Knowledge Transfer in Permutation Invariant Training for Single-Channel Multi-Talker Speech Recognition.
Tian TanYanmin QianDong YuPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- knowledge transfer
- single channel
- speech signal
- sound source
- multi channel
- knowledge sharing
- speech enhancement
- noisy environments
- automatic speech recognition
- language model
- hidden markov models
- speech synthesis
- transfer learning
- training set
- pattern recognition
- supervised learning
- independent component analysis
- frequency domain
- prior information
- brain activity
- active learning
- data mining
- multimedia
- image segmentation
- wavelet decomposition
- signal processing
- multi modal