/speech-recognition-papers

Towards hot directions in industrial end to end speech recognition

MIT LicenseMIT

Speech Recognition Papers

List of hot directions in industrial speech recognition, i.e., Streaming ASR (RNA-based || RNN-T based || Attention based || unified streaming/non-streaming) / Non-autoregressive ASR ...

If you are interested in this repo, any pull request is welcomed.

Streaming ASR

RNA based

RNN-T based

Attention based

Unified Streaming/Non-streaming models

Non-autoregressive (NAR) ASR

ASR Rescoring / Spelling Correction (2-pass decoding)

On-device ASR

Noisy Student Training(Self Training)

Self Supervised Learning(SSL)

APC(Autoregressive Predictive Coding)

CPC(Contrastive Predictive Coding)