Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS.
Kenta UdagawaYuki SaitoHiroshi SaruwatariPublished in: INTERSPEECH (2022)
Keyphrases
- speaker adaptation
- speech recognition
- speaker dependent
- maximum likelihood
- automatic speech recognition
- prosodic features
- human subjects
- text to speech
- speaker identification
- speaker independent
- language model
- image processing
- machine learning
- speaker verification
- speaker recognition
- neural network
- speech synthesis
- computer vision