paper-with-me

Keyword Spotting 벤치마크

Keyword Spotting on Google Speech Commands

43개 결과 · ⬇ CSV · JSON

Google Speech Commands V1 12

84.6 88.09 91.58 95.07 98.56 2017-11 2026-09 DS-CNN — 94.4 (2017-11-20) GRU — 93.5 (2017-11-20) LSTM — 92.9 (2017-11-20) Basic LSTM — 92.0 (2017-11-20) DNN — 91.6 (2017-11-20) CNN — 84.6 (2017-11-20) Attention RNN — 95.6 (2018-08-27) MatchboxNet-3x2x64 — 97.48 (2020-04-21) MHAtt-RNN — 97.2 (2020-05-14) res 8 — 97.8 (2020-08-21) NAS1 — 97.06 (2020-09-01) TripletLoss-res15 — 98.56 (2021-01-12) KWT-3 — 97.49 (2021-04-01) KWT-2 — 97.27 (2021-04-01) KWT-1 — 97.26 (2021-04-01) Wav2KWS — 97.9 (2021-05-10) BC-ResNet-8 — 98.0 (2021-06-08) ConvMixer — 97.3 (2022-01-15) SSAMBA — 96.9 (2024-05-20) DS-CNN — 94.4 (2017-11-20) Attention RNN — 95.6 (2018-08-27) MatchboxNet-3x2x64 — 97.48 (2020-04-21) res 8 — 97.8 (2020-08-21) TripletLoss-res15 — 98.56 (2021-01-12)
RankModel Google Speech Commands V1 12Google Speech Commands V2 12Google Speech Commands V2 2Google Speech Commands V2 20Google Speech Commands V2 35Google Speech Commands V1 2Google Speech Commands V1 20Google Speech Commands V1 35 PaperCodeYear
1 TripletLoss-res15 98.5698.37––97.0––– Learning Efficient Representations for Keyword Spotting with Triplet Loss roman-vygon/triplet_loss_kws 2021
2 BC-ResNet-8 98.098.7–––––– Broadcasted Residual Learning for Efficient Keyword Spotting google-research/google-research · Qualcomm-AI-research/bcresnet · re9ulus/BC-ResNet · +1 2021
3 Wav2KWS 97.998.5–97.8–––– Wav2KWS: Transfer Learning from Speech Representations for Keyword Spotting qute012/Wav2Keyword 2021
4 res 8 97.8––––––– Howl: A Deployed, Open-Source Wake Word Detection System castorini/howl · solyarisoftware/WeBAD 2020
5 KWT-3 97.49 ±0.1598.56 ±0.07––97.69 ±0.09––– Keyword Transformer: A Self-Attention Model for Keyword Spotting ARM-software/keyword-transformer · EscVM/EscVM_YT · ID56/Torch-KWT · +7 2021
6 MatchboxNet-3x2x64 97.4897.63–––––– MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition google-research/google-research 2020
7 ConvMixer 97.398.2–––––– ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting dianwen-ng/Keyword-Spotting-ConvMixer · IMvision12/keras-vision-models 2022
8 KWT-2 97.27 ±0.0898.43±0.08––97.74 ±0.03––– Keyword Transformer: A Self-Attention Model for Keyword Spotting ARM-software/keyword-transformer · EscVM/EscVM_YT · ID56/Torch-KWT · +7 2021
9 KWT-1 97.26±0.1898.08±0.10––96.95±0.14––– Keyword Transformer: A Self-Attention Model for Keyword Spotting ARM-software/keyword-transformer · EscVM/EscVM_YT · ID56/Torch-KWT · +7 2021
10 MHAtt-RNN 97.298–––––– Streaming keyword spotting on mobile devices google-research/google-research · qute012/Pytorch-MHAtt-RNN-KWS · Arizona-Voice/blossom 2020
1–10 / 43 다음 → 페이지당 10 20 50 100