Multilingual Speech Models for Automatic Speech Recognition Exhibit Gender Performance Gaps.
Giuseppe AttanasioBeatrice SavoldiDennis FucciDirk HovyPublished in: CoRR (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- acoustic models
- word error rate
- broadcast news
- conversational speech
- noisy environments
- spontaneous speech
- speech corpus
- spoken words
- speech sounds
- speech retrieval
- speech segments
- probabilistic model
- speaker identification
- speech recognition systems
- recognition errors
- linear prediction
- word recognition
- multi modal
- image processing