Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition.
Chao WengDong YuMichael L. SeltzerJasha DroppoPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2015)
Keyphrases
- speech recognition
- single channel
- neural network
- multi channel
- pattern recognition
- sound source
- speech signal
- language model
- hidden markov models
- automatic speech recognition
- speech recognizer
- speech enhancement
- speech synthesis
- speaker identification
- noisy environments
- speech recognition systems
- frequency domain
- prior information
- wavelet decomposition
- wiener filter
- independent component analysis
- multi modal
- vocal tract
- probabilistic model
- information retrieval