Neural Speech Separation Using Spatially Distributed Microphones.
Dongmei WangZhuo ChenTakuya YoshiokaPublished in: CoRR (2020)
Keyphrases
- spatially distributed
- speech signal
- automatic speech recognition
- sound source
- audio visual
- speech recognition
- network architecture
- environmental conditions
- neural network
- speaker identification
- multi modal
- automatic speech recognition systems
- bio inspired
- vocal tract
- hidden markov models
- noisy environments
- non stationary
- neural computation
- audio features
- broadcast news
- text to speech
- neural fuzzy
- data sets
- hebbian learning
- speech processing
- biologically plausible
- artificial intelligence
- learning rules
- visual information
- fundamental frequency
- computational neuroscience
- endpoint detection
- associative memory
- nonlinear predictive control
- artificial neural
- multi stream
- spike trains
- speaker recognition
- learning algorithm
- language acquisition
- blind source separation