Polyphone Disambiguation and Accent Prediction Using Pre-Trained Language Models in Japanese TTS Front-End.
Rem HidaMasaki HamadaChie KamadaEmiru TsunooToshiyuki SekiyaToshiyuki KumakuraPublished in: ICASSP (2022)
Keyphrases
- language model
- pre trained
- speech recognition
- language modeling
- probabilistic model
- n gram
- prediction accuracy
- document retrieval
- context sensitive
- language modelling
- information retrieval
- retrieval model
- query expansion
- smoothing methods
- statistical language models
- language models for information retrieval
- test collection
- relevance model
- training examples
- document ranking
- neural network
- co occurrence
- natural language
- translation model
- training data
- wordnet
- text classification
- cross lingual
- speech signal
- support vector
- clustering algorithm
- machine learning