Investigating the Utility of Surprisal from Large Language Models for Speech Synthesis Prosody.
Sofoklis KakourosJuraj SimkoMartti VainioAntti SuniPublished in: SSW (2023)
Keyphrases
- speech synthesis
- language model
- speech recognition
- language modeling
- prosodic features
- n gram
- vocal tract
- probabilistic model
- information retrieval
- document retrieval
- text to speech
- language modelling
- query expansion
- automatic speech recognition
- speech signal
- context sensitive
- retrieval model
- relevance model
- statistical language models
- test collection
- document ranking
- query terms
- noisy environments
- smoothing methods
- ad hoc information retrieval
- computer vision
- vector space model
- document collections
- pseudo relevance feedback
- pattern recognition
- language models for information retrieval