A speaker-dependent deep learning approach to joint speech separation and acoustic modeling for multi-talker automatic speech recognition.
Yanhui TuJun DuLi-Rong DaiChin-Hui LeePublished in: ISCSLP (2016)
Keyphrases
- automatic speech recognition
- speech recognition
- speaker dependent
- speaker independent
- deep learning
- speech signal
- phoneme recognition
- sound source
- speaker identification
- speech sounds
- acoustic features
- speech recognition systems
- hidden markov models
- broadcast news
- speaker adaptation
- speech recognizer
- acoustic models
- noisy environments
- speech synthesis
- conversational speech
- speech retrieval
- vocal tract
- mel frequency cepstral coefficients
- pattern recognition
- unsupervised learning
- speaker recognition
- language model
- machine learning
- speech corpus
- spontaneous speech
- speaker diarization
- digit recognition
- speaker verification
- non stationary
- audio visual