PGSS: Pitch-Guided Speech Separation.
Xiang LiYiwen WangYifan SunXihong WuJing ChenPublished in: AAAI (2023)
Keyphrases
- formant frequencies
- speech recognition
- fundamental frequency
- acoustic features
- speech signal
- automatic speech recognition
- speech synthesis
- language acquisition
- endpoint detection
- text to speech
- broadcast news
- audio stream
- vocal tract
- database
- spoken language
- audio visual
- speaker verification
- multi stream
- emotion recognition
- dialogue system
- recognition engine
- multi modal
- facial expressions
- real time