Speech and audio processing
A research field
Speech and audio processing is gaining ground in AI research: 1.3% to 1.5% of new AI papers, +0.2 points. It ranks #7 of 44 by gain in share. As of Oct 10, 2026.
- Change in share
- +0.2 pts
- Share, last 3 months
- 1.5%
- Papers, last 3 months
- 509
- Ready for products
- 2.6 / 5
Ideas in this field
Automatic speech recognition0.2% → 0.2%+0.1 ptsText to speech synthesis0.2% → 0.2%+0.0 ptsSpeech enhancement0.1% → 0.1%+0.0 ptsLow resource speech recognition0.1% → 0.0%0.0 ptsSpeaker diarization0.0% → 0.0%0.0 ptsSelf supervised speech representation0.1% → 0.0%0.0 ptsAudio language model0.1% → 0.1%0.0 ptsSpeech language model0.0% → 0.1%0.0 ptsConnectionist temporal classification0.0% → 0.0%0.0 ptsMultilingual speech recognition0.0% → 0.0%0.0 pts
Companies working on it
Speech and audio processing: quick answers
Yes. Its share of new AI papers went from 1.3% to 1.5%, with 509 papers in the last 3 months.