Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation.
Muhammad ShakeelYui SudoYifan PengShinji WatanabePublished in: CoRR (2024)
Keyphrases
- joint optimization
- automatic speech recognition
- speech recognition
- speech signal
- video streaming
- conversational speech
- low complexity
- recognition errors
- noisy environments
- spoken words
- word recognition
- machine learning
- question answering
- scalable video
- broadcast news
- error resilient
- signal processing
- nearest neighbor
- speech retrieval
- knn