Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features.
Alexandra VioniGeorgia ManiatiNikolaos EllinasJune Sig SungInchul HwangAimilios ChalamandarisPirros TsiakoulisPublished in: CoRR (2022)
Keyphrases
- text to speech
- content aware
- linguistic features
- text to speech synthesis
- prosodic features
- speech synthesis
- named entities
- structural features
- spontaneous speech
- text classification
- sentence level
- semantic features
- content delivery
- part of speech
- named entity recognition
- data mining
- linguistic knowledge
- speaker verification
- word processing
- news stories
- feature set
- feature space
- high level
- machine learning