TST: Time-Sparse Transducer for Automatic Speech Recognition.
Xiaohui ZhangMangui LiangZhengkun TianJiangyan YiJianhua TaoPublished in: CICAI (2) (2023)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- broadcast news
- noisy environments
- speech retrieval
- conversational speech
- spoken words
- spontaneous speech
- high dimensional
- word recognition
- recognition errors
- acoustic features
- sparse representation
- multi modal
- speech corpus
- language model
- document retrieval