Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition.
Takuya YoshiokaHakan ErdoganZhuo ChenFil AllevaPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- automatic speech recognition
- speech synthesis
- speech signal
- speech processing
- speech recognizer
- hidden markov models
- speaker identification
- speech recognition technology
- language model
- speech recognition systems
- speaker diarization
- pattern recognition
- speaker independent
- word error rate
- speaker recognition
- sound source
- neural network
- noisy environments
- speech recognizers
- broadcast news
- cepstral coefficients
- speech recognition errors
- audio visual speech recognition