Neural Speech Separation Using Spatially Distributed Microphones.
Dongmei WangZhuo ChenTakuya YoshiokaPublished in: INTERSPEECH (2020)
Keyphrases
- spatially distributed
- speech signal
- automatic speech recognition
- sound source
- audio visual
- speech recognition
- network architecture
- environmental conditions
- neural network
- automatic speech recognition systems
- speaker identification
- audio features
- hidden markov models
- noisy environments
- vocal tract
- linear prediction
- spoken dialogue systems
- speech synthesis
- artificial neural
- non stationary
- multi modal
- recognition engine
- neural model
- sound signals
- dialogue system
- bio inspired
- broadcast news
- video camera
- neural computation
- fitted q iteration
- single channel
- language acquisition
- independent component analysis
- dynamic environments