{"task":"Keyword Spotting","dataset":"Google Speech Commands","metric_names":["Google Speech Commands V1 12","Google Speech Commands V2 12","Google Speech Commands V2 2","Google Speech Commands V2 20","Google Speech Commands V2 35","Google Speech Commands V1 2","Google Speech Commands V1 20","Google Speech Commands V1 35"],"rows":[{"id":9224,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"TripletLoss-res15","metrics":{"Google Speech Commands V1 12":"98.56","Google Speech Commands V2 12":"98.37","Google Speech Commands V2 35":"97.0"},"paper_url":"https://arxiv.org/abs/2101.04792v4","paper_title":"Learning Efficient Representations for Keyword Spotting with Triplet Loss","paper_date":"2021-01-12","code_links":[{"title":"roman-vygon/triplet_loss_kws","url":"https://github.com/roman-vygon/triplet_loss_kws"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9225,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"BC-ResNet-8","metrics":{"Google Speech Commands V1 12":"98.0","Google Speech Commands V2 12":"98.7"},"paper_url":"https://arxiv.org/abs/2106.04140v4","paper_title":"Broadcasted Residual Learning for Efficient Keyword Spotting","paper_date":"2021-06-08","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"Qualcomm-AI-research/bcresnet","url":"https://github.com/Qualcomm-AI-research/bcresnet"},{"title":"re9ulus/BC-ResNet","url":"https://github.com/re9ulus/BC-ResNet"},{"title":"roman-vygon/BCResNet","url":"https://github.com/roman-vygon/BCResNet"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9226,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Wav2KWS","metrics":{"Google Speech Commands V1 12":"97.9","Google Speech Commands V2 12":"98.5","Google Speech Commands V2 20":"97.8"},"paper_url":"https://ieeexplore.ieee.org/document/9427206","paper_title":"Wav2KWS: Transfer Learning from Speech Representations for Keyword Spotting","paper_date":"2021-05-10","code_links":[{"title":"qute012/Wav2Keyword","url":"https://github.com/qute012/Wav2Keyword"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9227,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"res 8","metrics":{"Google Speech Commands V1 12":"97.8"},"paper_url":"https://arxiv.org/abs/2008.09606v1","paper_title":"Howl: A Deployed, Open-Source Wake Word Detection System","paper_date":"2020-08-21","code_links":[{"title":"castorini/howl","url":"https://github.com/castorini/howl"},{"title":"solyarisoftware/WeBAD","url":"https://github.com/solyarisoftware/WeBAD"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9228,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"KWT-3","metrics":{"Google Speech Commands V1 12":"97.49 ±0.15","Google Speech Commands V2 12":"98.56 ±0.07","Google Speech Commands V2 35":"97.69 ±0.09"},"paper_url":"https://arxiv.org/abs/2104.00769v3","paper_title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","paper_date":"2021-04-01","code_links":[{"title":"ARM-software/keyword-transformer","url":"https://github.com/ARM-software/keyword-transformer"},{"title":"EscVM/EscVM_YT","url":"https://github.com/EscVM/EscVM_YT/blob/master/Notebooks/1%20-%20TF2.X%20DeepAI-Quickie/tf_2_keyword_transformer.ipynb"},{"title":"ID56/Torch-KWT","url":"https://github.com/ID56/Torch-KWT"},{"title":"mashrurmorshed/torch-kwt","url":"https://github.com/mashrurmorshed/torch-kwt"},{"title":"holgerbovbjerg/data2vec-kws","url":"https://github.com/holgerbovbjerg/data2vec-kws"},{"title":"KrishnaDN/Keyword-Transformer","url":"https://github.com/KrishnaDN/Keyword-Transformer"},{"title":"intelligentmachines/keyword_spotting_transformer","url":"https://github.com/intelligentmachines/keyword_spotting_transformer"},{"title":"aau-es-ml/ssl_noise-robust_kws","url":"https://github.com/aau-es-ml/ssl_noise-robust_kws"},{"title":"Arizona-Voice/Arizona-spotting","url":"https://github.com/Arizona-Voice/Arizona-spotting"},{"title":"phanxuanphucnd/Arizona-spotting","url":"https://github.com/phanxuanphucnd/Arizona-spotting"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9229,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"MatchboxNet-3x2x64","metrics":{"Google Speech Commands V1 12":"97.48","Google Speech Commands V2 12":"97.63"},"paper_url":"http://arxiv.org/abs/2004.08531v2","paper_title":"MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition","paper_date":"2020-04-21","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9230,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"ConvMixer","metrics":{"Google Speech Commands V1 12":"97.3","Google Speech Commands V2 12":"98.2"},"paper_url":"https://arxiv.org/abs/2201.05863v1","paper_title":"ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting","paper_date":"2022-01-15","code_links":[{"title":"dianwen-ng/Keyword-Spotting-ConvMixer","url":"https://github.com/dianwen-ng/Keyword-Spotting-ConvMixer"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9231,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"KWT-2","metrics":{"Google Speech Commands V1 12":"97.27 ±0.08","Google Speech Commands V2 12":"98.43±0.08","Google Speech Commands V2 35":"97.74 ±0.03"},"paper_url":"https://arxiv.org/abs/2104.00769v3","paper_title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","paper_date":"2021-04-01","code_links":[{"title":"ARM-software/keyword-transformer","url":"https://github.com/ARM-software/keyword-transformer"},{"title":"EscVM/EscVM_YT","url":"https://github.com/EscVM/EscVM_YT/blob/master/Notebooks/1%20-%20TF2.X%20DeepAI-Quickie/tf_2_keyword_transformer.ipynb"},{"title":"ID56/Torch-KWT","url":"https://github.com/ID56/Torch-KWT"},{"title":"mashrurmorshed/torch-kwt","url":"https://github.com/mashrurmorshed/torch-kwt"},{"title":"holgerbovbjerg/data2vec-kws","url":"https://github.com/holgerbovbjerg/data2vec-kws"},{"title":"KrishnaDN/Keyword-Transformer","url":"https://github.com/KrishnaDN/Keyword-Transformer"},{"title":"intelligentmachines/keyword_spotting_transformer","url":"https://github.com/intelligentmachines/keyword_spotting_transformer"},{"title":"aau-es-ml/ssl_noise-robust_kws","url":"https://github.com/aau-es-ml/ssl_noise-robust_kws"},{"title":"Arizona-Voice/Arizona-spotting","url":"https://github.com/Arizona-Voice/Arizona-spotting"},{"title":"phanxuanphucnd/Arizona-spotting","url":"https://github.com/phanxuanphucnd/Arizona-spotting"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9232,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"KWT-1","metrics":{"Google Speech Commands V1 12":"97.26±0.18","Google Speech Commands V2 12":"98.08±0.10","Google Speech Commands V2 35":"96.95±0.14"},"paper_url":"https://arxiv.org/abs/2104.00769v3","paper_title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","paper_date":"2021-04-01","code_links":[{"title":"ARM-software/keyword-transformer","url":"https://github.com/ARM-software/keyword-transformer"},{"title":"EscVM/EscVM_YT","url":"https://github.com/EscVM/EscVM_YT/blob/master/Notebooks/1%20-%20TF2.X%20DeepAI-Quickie/tf_2_keyword_transformer.ipynb"},{"title":"ID56/Torch-KWT","url":"https://github.com/ID56/Torch-KWT"},{"title":"mashrurmorshed/torch-kwt","url":"https://github.com/mashrurmorshed/torch-kwt"},{"title":"holgerbovbjerg/data2vec-kws","url":"https://github.com/holgerbovbjerg/data2vec-kws"},{"title":"KrishnaDN/Keyword-Transformer","url":"https://github.com/KrishnaDN/Keyword-Transformer"},{"title":"intelligentmachines/keyword_spotting_transformer","url":"https://github.com/intelligentmachines/keyword_spotting_transformer"},{"title":"aau-es-ml/ssl_noise-robust_kws","url":"https://github.com/aau-es-ml/ssl_noise-robust_kws"},{"title":"Arizona-Voice/Arizona-spotting","url":"https://github.com/Arizona-Voice/Arizona-spotting"},{"title":"phanxuanphucnd/Arizona-spotting","url":"https://github.com/phanxuanphucnd/Arizona-spotting"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9233,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"MHAtt-RNN","metrics":{"Google Speech Commands V1 12":"97.2","Google Speech Commands V2 12":"98"},"paper_url":"https://arxiv.org/abs/2005.06720v2","paper_title":"Streaming keyword spotting on mobile devices","paper_date":"2020-05-14","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"qute012/Pytorch-MHAtt-RNN-KWS","url":"https://github.com/qute012/Pytorch-MHAtt-RNN-KWS"},{"title":"Arizona-Voice/blossom","url":"https://github.com/Arizona-Voice/blossom"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9234,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"NAS1","metrics":{"Google Speech Commands V1 12":"97.06"},"paper_url":"https://arxiv.org/abs/2009.00165v2","paper_title":"Neural Architecture Search For Keyword Spotting","paper_date":"2020-09-01","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9235,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"SSAMBA","metrics":{"Google Speech Commands V1 12":"96.9","Google Speech Commands V2 35":"97.4"},"paper_url":"https://arxiv.org/abs/2405.11831v2","paper_title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","paper_date":"2024-05-20","code_links":[{"title":"siavashshams/ssamba","url":"https://github.com/siavashshams/ssamba"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9236,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Attention RNN","metrics":{"Google Speech Commands V1 12":"95.6","Google Speech Commands V1 2":"99.2","Google Speech Commands V1 20":"94.1","Google Speech Commands V1 35":"94.3","Google Speech Commands V2 12":"96.9","Google Speech Commands V2 2":"99.4","Google Speech Commands V2 20":"94.5","Google Speech Commands V2 35":"93.9"},"paper_url":"http://arxiv.org/abs/1808.08929v1","paper_title":"A neural attention model for speech command recognition","paper_date":"2018-08-27","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"douglas125/SpeechCmdRecognition","url":"https://github.com/douglas125/SpeechCmdRecognition"},{"title":"huckiyang/speech_quantum_dl","url":"https://github.com/huckiyang/speech_quantum_dl"},{"title":"huckiyang/QuantumSpeech-QCNN","url":"https://github.com/huckiyang/QuantumSpeech-QCNN"},{"title":"renyuanL/ry-Speech-commands","url":"https://github.com/renyuanL/ry-Speech-commands"},{"title":"Arizona-Voice/blossom","url":"https://github.com/Arizona-Voice/blossom"},{"title":"httttttt/ResNetAtentionBiLSTM","url":"https://github.com/httttttt/ResNetAtentionBiLSTM"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9237,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"DS-CNN","metrics":{"Google Speech Commands V1 12":"94.4"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9238,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"GRU","metrics":{"Google Speech Commands V1 12":"93.5"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":1,"source":"archive","tags":[]},{"id":9239,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"LSTM","metrics":{"Google Speech Commands V1 12":"92.9"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":1,"source":"archive","tags":[]},{"id":9240,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Basic LSTM","metrics":{"Google Speech Commands V1 12":"92.0"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9241,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"DNN","metrics":{"Google Speech Commands V1 12":"91.6"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9242,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"CNN","metrics":{"Google Speech Commands V1 12":"84.6"},"paper_url":"http://arxiv.org/abs/1711.07128v3","paper_title":"Hello Edge: Keyword Spotting on Microcontrollers","paper_date":"2017-11-20","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"ARM-software/ML-KWS-for-MCU","url":"https://github.com/ARM-software/ML-KWS-for-MCU"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/nlp/dscnn"},{"title":"UT2UH/ML-KWS-for-ESP32","url":"https://github.com/UT2UH/ML-KWS-for-ESP32"},{"title":"Lebhoryi/ML-KWS-for-MCU","url":"https://github.com/Lebhoryi/ML-KWS-for-MCU"},{"title":"etrommer/dcsr","url":"https://github.com/etrommer/dcsr"},{"title":"Anustup900/Tensorflow-Speech-Recognition","url":"https://github.com/Anustup900/Tensorflow-Speech-Recognition"},{"title":"widzemin/audio_project","url":"https://github.com/widzemin/audio_project"},{"title":"jayant766/MIDAS-IIITD","url":"https://github.com/jayant766/MIDAS-IIITD"},{"title":"hustxsl/C-ML-KWS-for-MCU","url":"https://github.com/hustxsl/C-ML-KWS-for-MCU"},{"title":"Paulonso/ARM-software","url":"https://github.com/Paulonso/ARM-software"},{"title":"Jaskaran197/KWS-TF-MCU","url":"https://github.com/Jaskaran197/KWS-TF-MCU"},{"title":"FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints","url":"https://github.com/FraCorti/Deep_Subnetworks_for_Dynamic_Resource_Constraints"},{"title":"magahub/KWS-ARM","url":"https://github.com/magahub/KWS-ARM"},{"title":"BgLoveXixi/Keyword_recognition","url":"https://github.com/BgLoveXixi/Keyword_recognition"},{"title":"fracorti/reds","url":"https://github.com/fracorti/reds"},{"title":"Paulonso/ML-KWS-for-MCU","url":"https://github.com/Paulonso/ML-KWS-for-MCU"},{"title":"robin-ai-ml/ML-KWS-for-MCU","url":"https://github.com/robin-ai-ml/ML-KWS-for-MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9243,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"WaveFormer","metrics":{"Google Speech Commands V2 12":"98.8","Google Speech Commands V2 35":"99.1"},"paper_url":"https://ieeexplore.ieee.org/document/10546828","paper_title":"Work in Progress: Linear Transformers for TinyML","paper_date":"2024-03-25","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9244,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"EdgeCRNN 2.0×","metrics":{"Google Speech Commands V2 12":"98.05"},"paper_url":"https://link.springer.com/article/10.1007/s12652-021-03022-1","paper_title":"EdgeCRNN: an edgecomputing oriented model of acoustic feature enhancement for keyword spotting","paper_date":"2021-03-14","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9245,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Embedding + Head","metrics":{"Google Speech Commands V2 12":"97.7"},"paper_url":"https://arxiv.org/abs/2002.01322v1","paper_title":"Training Keyword Spotters with Limited and Synthesized Speech Data","paper_date":"2020-01-31","code_links":[{"title":"dscripka/openwakeword","url":"https://github.com/dscripka/openwakeword"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9246,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Head without Embedding","metrics":{"Google Speech Commands V2 12":"97.4"},"paper_url":"https://arxiv.org/abs/2002.01322v1","paper_title":"Training Keyword Spotters with Limited and Synthesized Speech Data","paper_date":"2020-01-31","code_links":[{"title":"dscripka/openwakeword","url":"https://github.com/dscripka/openwakeword"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9247,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"TC-ResNet14-1.5","metrics":{"Google Speech Commands V2 12":"96.6"},"paper_url":"https://arxiv.org/abs/1904.03814v2","paper_title":"Temporal Convolution for Real-time Keyword Spotting on Mobile Devices","paper_date":"2019-04-08","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/kws_streaming"},{"title":"hyperconnect/TC-ResNet","url":"https://github.com/hyperconnect/TC-ResNet"},{"title":"Alex-Riviello/KWS_MCU","url":"https://github.com/Alex-Riviello/KWS_MCU"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9248,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"End-to-end KWS model","metrics":{"Google Speech Commands V2 12":"95.55"},"paper_url":"https://arxiv.org/abs/2104.06666v1","paper_title":"End-to-end Keyword Spotting using Neural Architecture Search and Quantization","paper_date":"2021-04-14","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9249,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"MicroNet-KWS-L","metrics":{"Google Speech Commands V2 12":"95.3"},"paper_url":"https://arxiv.org/abs/2010.11267v6","paper_title":"MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers","paper_date":"2020-10-21","code_links":[{"title":"ARM-software/ML-zoo","url":"https://github.com/ARM-software/ML-zoo"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9250,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"DenseNet-BiLTSM","metrics":{"Google Speech Commands V2 20":"96.6"},"paper_url":"https://ieeexplore.ieee.org/document/8607038","paper_title":"Effective Combination of DenseNet andBiLSTM for Keyword Spotting","paper_date":"2019-01-19","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9251,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"LSTM","metrics":{"Google Speech Commands V2 20":"93.72"},"paper_url":"https://arxiv.org/abs/1907.04536v1","paper_title":"Multi-layer Attention Mechanism for Speech Keyword Recognition","paper_date":"2019-07-10","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9252,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"QNN","metrics":{"Google Speech Commands":"98.53","Google Speech Commands V2 35":"98.60"},"paper_url":"https://ieeexplore.ieee.org/document/10248052","paper_title":"Towards on-Device Keyword Spotting using Low-Footprint Quaternion Neural Models","paper_date":"2023-09-15","code_links":[{"title":"DataSenseiAryan/GoogleSpeechCommandLowFootprint","url":"https://github.com/DataSenseiAryan/GoogleSpeechCommandLowFootprint"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9253,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"M2D","metrics":{"Google Speech Commands V2 35":"98.5"},"paper_url":"https://arxiv.org/abs/2210.14648v3","paper_title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","paper_date":"2022-10-26","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9254,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"EAT-S","metrics":{"Google Speech Commands V2 35":"98.15"},"paper_url":"https://arxiv.org/abs/2204.11479v5","paper_title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","paper_date":"2022-04-25","code_links":[{"title":"Alibaba-MIIL/AudioClassfication","url":"https://github.com/Alibaba-MIIL/AudioClassfication"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9255,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Audio Spectrogram Transformer","metrics":{"Google Speech Commands V2 35":"98.11"},"paper_url":"https://arxiv.org/abs/2104.01778v3","paper_title":"AST: Audio Spectrogram Transformer","paper_date":"2021-04-05","code_links":[{"title":"YuanGongND/ast","url":"https://github.com/YuanGongND/ast"},{"title":"nttcslab/composing-general-audio-repr","url":"https://github.com/nttcslab/composing-general-audio-repr"},{"title":"pxaris/ccml","url":"https://github.com/pxaris/ccml"},{"title":"cgaroufis/msspt","url":"https://github.com/cgaroufis/msspt"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/audio_spectrogram_transformer"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9256,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"HTS-AT","metrics":{"Google Speech Commands V2 35":"98.0"},"paper_url":"https://arxiv.org/abs/2202.00874v1","paper_title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","paper_date":"2022-02-02","code_links":[{"title":"retrocirce/hts-audio-transformer","url":"https://github.com/retrocirce/hts-audio-transformer"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9257,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"KW-MLP","metrics":{"Google Speech Commands V2 35":"97.56"},"paper_url":"https://arxiv.org/abs/2110.07749v3","paper_title":"Attention-Free Keyword Spotting","paper_date":"2021-10-14","code_links":[{"title":"AI-Research-BD/Keyword-MLP","url":"https://github.com/AI-Research-BD/Keyword-MLP"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9258,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"ImportantAug","metrics":{"Google Speech Command-Musan":"86.7","Google Speech Commands V2 35":"95"},"paper_url":"https://arxiv.org/abs/2112.07156v2","paper_title":"ImportantAug: a data augmentation agent for speech","paper_date":"2021-12-14","code_links":[{"title":"tvanh512/importantAug","url":"https://github.com/tvanh512/importantAug"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9259,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"NAS2","metrics":{"Google Speech Commands V1 6":"97.22"},"paper_url":"https://arxiv.org/abs/2009.00165v2","paper_title":"Neural Architecture Search For Keyword Spotting","paper_date":"2020-09-01","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9260,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"Quantum CNN","metrics":{"10-keyword Speech Commands dataset":"95.12"},"paper_url":"https://arxiv.org/abs/2010.13309v2","paper_title":"Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition","paper_date":"2020-10-26","code_links":[{"title":"huckiyang/speech_quantum_dl","url":"https://github.com/huckiyang/speech_quantum_dl"},{"title":"huckiyang/QuantumSpeech-QCNN","url":"https://github.com/huckiyang/QuantumSpeech-QCNN"}],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9261,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"TDNN","metrics":{"10-keyword Speech Commands dataset":"94.3"},"paper_url":"http://arxiv.org/abs/1807.04353v2","paper_title":"Efficient keyword spotting using time delay neural networks","paper_date":"2018-08-28","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9262,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"PATE-AAE (Differentially-Private)","metrics":{"10-keyword Speech Commands dataset":"92.37"},"paper_url":"https://arxiv.org/abs/2104.01271v2","paper_title":"PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification","paper_date":"2021-04-02","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9263,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"res8 w/ SSN(S=4, A=Sub)","metrics":{"% Test Accuracy":"95.4% ±0.22"},"paper_url":"https://arxiv.org/abs/2103.13620v1","paper_title":"SubSpectral Normalization for Neural Audio Data Processing","paper_date":"2021-03-25","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9264,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"res15 w/ SSN(S=4, A=Sub)","metrics":{"% Test Accuracy":"96.8% ±0.13"},"paper_url":"https://arxiv.org/abs/2103.13620v1","paper_title":"SubSpectral Normalization for Neural Audio Data Processing","paper_date":"2021-03-25","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":9265,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"res15 w/ SSN(S=4, A=Sub) (2019)","metrics":{"% Test Accuracy":"97.5% ±0.15"},"paper_url":"https://arxiv.org/abs/2103.13620v1","paper_title":"SubSpectral Normalization for Neural Audio Data Processing","paper_date":"2021-03-25","code_links":[],"metrics_order":"[\"Google Speech Commands V1 12\", \"Google Speech Commands V2 12\", \"Google Speech Commands V2 2\", \"Google Speech Commands V2 20\", \"Google Speech Commands V2 35\", \"Google Speech Commands V1 2\", \"Google Speech Commands V1 20\", \"Google Speech Commands V1 35\", \"Google Speech Commands V1 6\", \"10-keyword Speech Commands dataset\", \"Google Speech Command-Musan\", \"% Test Accuracy\", \"Google Speech Commands\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":670161,"task":"Keyword Spotting","parent_task":null,"dataset":"Google Speech Commands","model_name":"End-to-End Keyword Spotting on FPGA Usin","metrics":{"Google Speech Commands":"87.43"},"paper_url":"https://paperswithcode.com/paper/end-to-end-keyword-spotting-on-fpga-using-graph-neural-networks-with-a-neuromorphic-auditory-sensor","paper_title":"End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor","paper_date":"2026-05-10","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}