Speech Recognition
Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.
( Image credit: SpecAugment )
Papers
Showing 1–10 of 6433 papers
All datasetsLibriSpeech test-cleanLibriSpeech test-otherSwitchboard + Hub500TIMITAISHELL-1WSJ eval92Common Voice Germanswb_hub_500 WER fullSWBCHTUDACommon Voice FrenchCommon Voice SpanishMediaSpeech
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PocketSphinx | Test WER | 39.6 | — | Unverified |
| 2 | Kaldi | Test WER | 20.5 | — | Unverified |
| 3 | DeepSpeech-Polyglot | Test WER | 18.6 | — | Unverified |
| 4 | Kaldi | Test WER | 14.4 | — | Unverified |
| 5 | Hybrid CTC/Attention | Test WER | 12.8 | — | Unverified |
| 6 | IMS-Speech | Test WER | 12 | — | Unverified |
| 7 | QuartzNet15x5DE (D37) | Test WER | 10.2 | — | Unverified |
| 8 | TDNN-HMM hybrid, FST (with RNNLM rescoring) | Test WER | 6.93 | — | Unverified |
| 9 | Conformer-Transducer (no LM) | Test WER | 5.82 | — | Unverified |