An Unsupervised Two-Talker Speech Separation System Based on CASA.
Hongyan LiYue WangRongrong ZhaoXueying ZhangPublished in: Int. J. Pattern Recognit. Artif. Intell. (2018)
Keyphrases
- speech recognition
- sound source
- audio visual
- semi supervised
- endpoint detection
- speech synthesis
- spoken dialogue systems
- automatic speech recognition
- unsupervised learning
- real world objects
- spoken language
- speaker identification
- english text
- completely unsupervised
- noisy environments
- emotion recognition
- audio features
- broadcast news
- data driven
- speaker recognition
- supervised learning
- natural language