Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation.
Zhonghua LiuShijun WangNing ChenPublished in: INTERSPEECH (2023)
Keyphrases
- text to speech
- speech recognition
- speech synthesis
- emotion recognition
- voice activity detection
- fundamental frequency
- spoken language
- speech processing
- speech music discrimination
- endpoint detection
- speech quality
- speech signal
- audio visual
- dialogue system
- speech recognition errors
- speech sounds
- automatic speech recognition systems
- linear prediction
- speaker recognition
- spectral features
- spoken dialogue systems
- spontaneous speech
- recognition engine
- noisy environments
- text to speech synthesis
- hearing impaired
- gaussian mixture model