Deep beamforming networks for multi-channel speech recognition.
Xiong XiaoShinji WatanabeHakan ErdoganLiang LuJohn R. HersheyMichael L. SeltzerGuoguo ChenYu ZhangMichael I. MandelDong YuPublished in: ICASSP (2016)
Keyphrases
- speech recognition
- multi channel
- single channel
- speech enhancement
- language model
- hidden markov models
- pattern recognition
- speech synthesis
- speech signal
- automatic speech recognition
- speech recognizer
- speech processing
- speaker identification
- speech recognition technology
- noisy environments
- speech recognition systems
- speech recognizers
- speech retrieval
- multiscale
- speaker independent
- speaker dependent