Multi-channel feature adaptation for robust speech recognition.
Zhaofeng ZhangXiong XiaoLongbiao WangJianwu DangMasahiro IwahashiEng Siong ChngHaizhou LiPublished in: ISCSLP (2016)
Keyphrases
- speech recognition
- multi channel
- noisy environments
- speaker adaptation
- hidden markov models
- language model
- automatic speech recognition
- cepstral coefficients
- pattern recognition
- speech synthesis
- speech signal
- single channel
- speech processing
- speech recognizer
- speech recognition systems
- multi modal
- speaker identification
- audio visual speech recognition
- speech retrieval
- feature selection
- machine learning
- multi stream
- multiresolution
- feature vectors
- speaker independent
- multiscale
- neural network