FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition.
Yichong LengXu TanRui WangLinchen ZhuJin XuWenjie LiuLinquan LiuXiang-Yang LiTao QinEdward LinTie-Yan LiuPublished in: EMNLP (Findings) (2021)
Keyphrases
- error correction
- automatic speech recognition
- speech recognition
- speech signal
- error detection
- data hiding
- speech retrieval
- conversational speech
- word recognition
- machine learning
- watermarking scheme
- language model
- hidden markov models
- multiresolution
- pattern recognition
- broadcast news
- error correcting
- spontaneous speech
- recognition errors
- speech corpus
- error detection and correction
- neural network