Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer.
Jing-Xuan ZhangLi-Juan LiuYan-Nian ChenYa-Jun HuYuan JiangZhen-Hua LingLi-Rong DaiPublished in: CoRR (2020)
Keyphrases
- text to speech
- automatic speech recognition
- text to speech synthesis
- speech recognition
- speech synthesis
- hidden markov models
- speech signal
- speech corpus
- prosodic features
- spoken words
- broadcast news
- word error rate
- conversational speech
- word processing
- speech sounds
- speech retrieval
- acoustic features
- recognition errors
- word recognition
- noisy environments
- transfer learning
- neural network
- vocal tract
- text classification
- language model
- denoising
- machine learning