Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training.
Yanmin QianXuankai ChangDong YuPublished in: CoRR (2017)
Keyphrases
- speech recognition
- single channel
- speech signal
- sound source
- multi channel
- isolated word
- hidden markov models
- pattern recognition
- speech synthesis
- automatic speech recognition
- speech enhancement
- language model
- speech recognizer
- noisy environments
- acoustic models
- speech recognition systems
- wavelet decomposition
- frequency domain
- prior information
- image processing
- wiener filter
- vocal tract
- signal processing
- training data
- speaker independent
- face recognition