Transduce and Speak: Neural Transducer for Text-To-Speech with Semantic Token Prediction.
Minchan KimMyeonghun JeongByoung Jin ChoiDongjune LeeNam Soo KimPublished in: ASRU (2023)
Keyphrases
- text to speech
- speech synthesis
- prediction accuracy
- text to speech synthesis
- neural network
- semantic web
- prediction error
- network architecture
- natural language
- prosodic features
- semantic similarity
- prediction algorithm
- liquid state machine
- programming tool
- semantic annotation
- high level
- semantic analysis
- semantic knowledge
- prediction model
- word processing
- domain specific
- semantic features
- english text
- domain independent
- semantic information
- online learning