Self-Critical Sequence Training for Automatic Speech Recognition.
Chen ChenYuchen HuNana HouXiaofeng QiHeqing ZouEng Siong ChngPublished in: ICASSP (2022)
Keyphrases
- automatic speech recognition
- discriminative training
- speech recognition
- speech signal
- broadcast news
- hidden markov models
- word error rate
- acoustic models
- spoken words
- speech retrieval
- word recognition
- conversational speech
- noisy environments
- recognition errors
- viterbi algorithm
- computer vision
- acoustic features
- query expansion
- multi modal
- pattern recognition
- feature extraction
- feature selection