Bi-Level Speaker Supervision for One-Shot Speech Synthesis.
Tao WangJianhua TaoRuibo FuJiangyan YiZhengqi WenChunyu QiangPublished in: INTERSPEECH (2020)
Keyphrases
- bi level
- speech synthesis
- prosodic features
- speech recognition
- vocal tract
- text to speech
- gray scale
- automatic speech recognition
- pricing model
- language model
- speaker identification
- speech signal
- pattern recognition
- speech corpus
- speaker diarization
- hidden markov models
- speaker dependent
- speaker verification
- image compression
- noisy environments
- speaker recognition
- active learning
- audio visual
- life cycle
- wavelet transform
- multiresolution
- speaker adaptation
- data sets