A unified network for multi-speaker speech recognition with multi-channel recordings.
Conggui LiuNakamasa InoueKoichi ShinodaPublished in: APSIPA (2017)
Keyphrases
- speech recognition
- multi channel
- single channel
- hidden markov models
- automatic speech recognition
- pattern recognition
- speech recognition technology
- speaker identification
- speech synthesis
- speech processing
- noisy environments
- speech signal
- speaker diarization
- speech recognizer
- speech recognition systems
- language model
- speaker independent
- wireless mesh networks
- speaker dependent
- spontaneous speech
- speaker adaptation
- speaker recognition
- cellular networks
- multiscale
- acoustic models
- neural network
- multiresolution
- speech retrieval
- machine learning