One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for Speech Recognition.
Zhengkun TianJiangyan YiYe BaiJianhua TaoShuai ZhangZhengqi WenPublished in: APSIPA ASC (2021)
Keyphrases
- speech recognition
- hidden markov models
- automatic speech recognition
- pattern recognition
- speech signal
- speech processing
- language model
- speech synthesis
- speech understanding
- noisy environments
- speaker identification
- speech recognizer
- speech recognizers
- speech recognition technology
- speaker independent
- handwriting recognition
- neural network
- computer vision
- cepstral coefficients
- speaker dependent
- speaker diarization
- word recognition
- audio visual speech recognition