# Speech and audio language models

8,980 papers in 11 research directions. Data through 19 Oct 2026.
HTML: https://mlsanity.com/speech/

## Directions (largest first)

- [Speech recognition models and training](https://mlsanity.com/speech/speech-recognition-models-and-training/index.md): 1,811 papers, 3 new this week
- [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/index.md): 1,631 papers, 2 new this week
- [Multilingual and low-resource ASR](https://mlsanity.com/speech/multilingual-and-low-resource-asr/index.md): 1,075 papers, 3 new this week
- [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/index.md): 892 papers, 0 new this week
- [Speaker recognition and diarization](https://mlsanity.com/speech/speaker-recognition-and-diarization/index.md): 832 papers, 2 new this week
- [Audio language models and spoken dialogue](https://mlsanity.com/speech/audio-language-models-and-spoken-dialogue/index.md): 739 papers, 1 new this week
- [ASR evaluation, bias and atypical speech](https://mlsanity.com/speech/asr-evaluation-bias-and-atypical-speech/index.md): 644 papers, 3 new this week
- [Anti-spoofing and adversarial audio attacks](https://mlsanity.com/speech/anti-spoofing-and-adversarial-audio-attacks/index.md): 449 papers, 0 new this week
- [Speech translation](https://mlsanity.com/speech/speech-translation/index.md): 365 papers, 0 new this week
- [Audio-visual speech recognition](https://mlsanity.com/speech/audio-visual-speech-recognition/index.md): 283 papers, 0 new this week
- [Emotional speech synthesis and recognition](https://mlsanity.com/speech/emotional-speech-synthesis-and-recognition/index.md): 259 papers, 1 new this week