Scene-aware Far-field Automatic Speech Recognition.
Zhenyu TangDinesh ManochaPublished in: CoRR (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- speech signal
- speech retrieval
- broadcast news
- conversational speech
- video sequences
- word error rate
- spoken words
- recognition errors
- acoustic features
- word recognition
- noisy environments
- input image
- spontaneous speech
- compound words
- natural images
- image retrieval
- machine learning