Reexamining Racial Disparities in Automatic Speech Recognition Performance: The Role of Confounding by Provenance.
Changye LiTrevor CohenSerguei PakhomovPublished in: CoRR (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- broadcast news
- conversational speech
- hidden markov models
- speech retrieval
- metadata
- united states
- noisy environments
- word recognition
- acoustic features
- recognition errors
- spoken words
- speech corpus
- speaker adaptation
- spontaneous speech
- language model
- multiscale