speech recognition
- Papers
- 6
- Released code
- 0
- First seen
- Sept 2026
- Latest
- Oct 2026
6 papers in the last two months, against 0 in the two before.
The papers
Most central to this idea first, not most recent.
- Academiccs.CL
Compression Widens Demographic Fairness Gaps in Whisper Speech Recognition Models
The Ohio State University, Air Force Research Laboratory · Oct 2026
- Chinese Techeess.AS
Pruned CTC cuts memory for large-vocabulary ASR training without sacrificing accuracy.
Shanghai Jiao Tong University, University of Cambridge · Oct 2026
- Big Tech
Audio LLMs cannot assess their own transcription reliability.
Apple, University of California San Diego · Sept 2026
- Top University
Open YODAS v3 corpus delivers 1.1 million hours of stereo speech
Carnegie Mellon University, Keio University · Oct 2026
- Big Techcs.CL
Open voice model combines real-time conversation with native tool calling
NVIDIA · Sept 2026
- Independentcs.AI
Voice-agent models diverge most beyond choosing the correct tool
Sept 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.