Training Multi-Speaker Neural Text-to-Speech Systems Using Speaker-Imbalanced Speech Corpora.
Hieu-Thi LuongXin WangJunichi YamagishiNobuyuki NishizawaPublished in: INTERSPEECH (2019)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- speech recognition
- speaker verification
- automatic speech recognition systems
- audio visual
- speaker recognition
- automatic speech recognition
- automatic transcription
- text to speech synthesis
- neural network
- spontaneous speech
- vocal tract
- speaker diarization
- speaker identification
- speech signal
- network architecture
- speaker independent
- training set
- test set
- acoustic models
- speaker dependent
- english text
- speech recognition systems
- pattern recognition
- emotion recognition
- hearing impaired
- software developers