Sound source separation for plural passenger speech recognition in smart mobility system.
Masahiro FukuiYouhei WakisakaToshihiko WatanabeMinato KanazawaPublished in: ICCE (2018)
Keyphrases
- speech recognition
- source separation
- blind source separation
- speech signal
- sound source
- independent component analysis
- audio features
- automatic speech recognition
- hidden markov models
- language model
- denoising
- temporal structure
- pattern recognition
- single channel
- speaker identification
- speech recognition systems
- noisy environments
- non stationary
- audio visual
- machine learning