Unsupervised Speech Recognition Alexei Baevski
–Neural Information Processing Systems
This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data.
Neural Information Processing Systems
Nov-16-2025, 00:13:21 GMT
- Country:
- Europe
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- United Kingdom > Scotland
- City of Edinburgh > Edinburgh (0.04)
- Italy > Calabria
- North America > Mexico
- Gulf of Mexico (0.04)
- Europe
- Technology: