Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction.
Minchan KimMyeonghun JeongByoung Jin ChoiSemin KimJoun Yeop LeeNam Soo KimPublished in: CoRR (2024)
Keyphrases
- text to speech
- speech synthesis
- prediction accuracy
- prediction algorithm
- text to speech synthesis
- prosodic features
- programming tool
- network architecture
- semantic knowledge
- liquid state machine
- semantic web
- semantic information
- neural network
- semantic features
- prediction error
- semantic search
- semantic description
- english text
- semantic annotation
- bio inspired
- associative memory
- prediction model
- domain ontology
- domain specific
- object oriented
- natural language
- high level
- semantic similarity
- domain independent
- software engineering