TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Attention RNN

Attention RNN

Reported on 8 benchmarks across 1 task · 1 paper · 8 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech8 results

  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V1 12· 2018-08-27
    95.6
    best: 98.56 (TripletLoss-res15)
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V1 2· 2018-08-27
    99.2
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V1 20· 2018-08-27
    94.1
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V1 35· 2018-08-27
    94.3
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V2 12· 2018-08-27
    96.9
    best: 98.8 (WaveFormer)
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V2 2· 2018-08-27
    99.4
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V2 20· 2018-08-27
    94.5
    best: 97.8 (Wav2KWS)
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929
  • Keyword SpottingonGoogle Speech Commands
    Google Speech Commands V2 35· 2018-08-27
    93.9
    best: 99.1 (WaveFormer)
    SOTA
    A neural attention model for speech command recognitionarXiv:1808.08929