High-Intelligibility Speech Synthesis for Dysarthric Speakers with LPCNet-Based TTS and CycleVAE-Based VC.
Keisuke MatsubaraTakuma OkamotoRyoichi TakashimaTetsuya TakiguchiTomoki TodaYoshinori ShigaHisashi KawaiPublished in: ICASSP (2021)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- hidden markov models
- vocal tract
- language model
- automatic speech recognition
- speech signal
- speaker identification
- pattern recognition
- database
- noisy environments
- speech corpus
- speaker dependent
- high precision
- wide range
- decision trees
- computer vision
- databases
- non stationary
- objective function
- word processing
- e learning
- artificial intelligence
- data mining