{"task":"Spoken Command Recognition","dataset":"Speech Command v2","metric_names":["Accuracy"],"rows":[{"id":127261,"task":"Spoken Command Recognition","parent_task":null,"dataset":"Speech Command v2","model_name":"SSAST-FRAME","metrics":{"Accuracy":"98.1"},"paper_url":"https://arxiv.org/abs/2110.09784v2","paper_title":"SSAST: Self-Supervised Audio Spectrogram Transformer","paper_date":"2021-10-19","code_links":[{"title":"YuanGongND/ast","url":"https://github.com/YuanGongND/ast"},{"title":"YuanGongND/ssast","url":"https://github.com/YuanGongND/ssast"},{"title":"siavashshams/ssamba","url":"https://github.com/siavashshams/ssamba"}],"metrics_order":"[\"Accuracy\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":127262,"task":"Spoken Command Recognition","parent_task":null,"dataset":"Speech Command v2","model_name":"Base (ours)","metrics":{"Accuracy":"98.0"},"paper_url":"https://arxiv.org/abs/2204.12076v3","paper_title":"ATST: Audio Representation Learning with Teacher-Student Transformer","paper_date":"2022-04-26","code_links":[{"title":"Audio-WestlakeU/ATST-SED","url":"https://github.com/Audio-WestlakeU/ATST-SED"},{"title":"Audio-WestlakeU/audiossl","url":"https://github.com/Audio-WestlakeU/audiossl/tree/main/audiossl/methods/atst"},{"title":"2024-MindSpore-1/Code6","url":"https://github.com/2024-MindSpore-1/Code6/tree/main/ats"},{"title":"2023-MindSpore-4/Code8","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/ats"}],"metrics_order":"[\"Accuracy\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":127263,"task":"Spoken Command Recognition","parent_task":null,"dataset":"Speech Command v2","model_name":"SSAST-PATCH","metrics":{"Accuracy":"98.0"},"paper_url":"https://arxiv.org/abs/2110.09784v2","paper_title":"SSAST: Self-Supervised Audio Spectrogram Transformer","paper_date":"2021-10-19","code_links":[{"title":"YuanGongND/ast","url":"https://github.com/YuanGongND/ast"},{"title":"YuanGongND/ssast","url":"https://github.com/YuanGongND/ssast"},{"title":"siavashshams/ssamba","url":"https://github.com/siavashshams/ssamba"}],"metrics_order":"[\"Accuracy\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]},{"id":127264,"task":"Spoken Command Recognition","parent_task":null,"dataset":"Speech Command v2","model_name":"COLA","metrics":{"Accuracy":"95.5"},"paper_url":"https://arxiv.org/abs/2010.10915v1","paper_title":"Contrastive Learning of General-Purpose Audio Representations","paper_date":"2020-10-21","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/cola"},{"title":"SarthakYadav/audax","url":"https://github.com/SarthakYadav/audax/tree/master/recipes/cola"}],"metrics_order":"[\"Accuracy\"]","area":"Speech","uses_additional_data":0,"source":"archive","tags":[]}]}