Accent and Speaker Disentanglement in Many-to-many Voice Conversion.
Zhichao WangWenshuo GeXiong WangShan YangWendong GanHaitao ChenHai LiLei XieXiulin LiPublished in: CoRR (2020)
Keyphrases
- speech recognition
- automatic speech recognition
- prosodic features
- synthesized speech
- speech synthesis
- speech sounds
- voice activity detection
- mel frequency cepstral coefficients
- speaker identification
- text to speech
- speaker verification
- speaker diarization
- hidden markov models
- audio visual
- spoken language
- language model
- speech signal
- emotion recognition
- pattern recognition
- vocal tract
- data sets
- broadcast news
- speaker adaptation
- speaker dependent
- speaker recognition
- database
- noisy environments
- machine learning
- neural network
- speech quality
- case study
- knowledge base
- artificial intelligence
- interactive voice response