On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis.
Cheng-I Jeff LaiErica CooperYang ZhangShiyu ChangKaizhi QianYi-Lun LiaoYung-Sung ChuangAlexander H. LiuJunichi YamagishiDavid CoxJames R. GlassPublished in: CoRR (2021)
Keyphrases
- speech synthesis
- speech recognition
- text to speech
- vocal tract
- prosodic features
- hidden markov models
- language model
- automatic speech recognition
- sparse representation
- speech corpus
- high dimensional
- speech signal
- pattern recognition
- cross domain collaborative filtering
- feature extraction
- noisy environments
- bayesian networks