BROWSE
Detail
Journal Article
Modality-Based Sentence-Final Intonation Prediction for Korean Conversational-Style Text-to-Speech Systems
- Authors
- Seung Shin Oh, Sang Hun Kim
- Issue Date
- 2006-12
- Citation
- ETRI Journal, v.28, no.6, pp.807-810
- ISSN
- 1225-6463
- Publisher
- 한국전자통신연구원 (ETRI)
- Language
- English
- Type
- Journal Article
- Abstract
- This letter presents a prediction model for sentence-final intonations for Korean conversational-style text-to-speech systems in which we introduce the linguistic feature of 'modality' as a new parameter. Based on their function and meaning, we classify tonal forms in speech data into tone types meaningful for speech synthesis and use the result of this classification to build our prediction model using a tree structured classification algorithm. In order to show that modality is more effective for the prediction model than features such as sentence type or speech act, an experiment is performed on a test set of 970 utterances with a training set of 3,883 utterances. The results show that modality makes a higher contribution to the determination of sentence-final intonation than sentence type or speech act, and that prediction accuracy improves up to 25% when the feature of modality is introduced.
- KSP Keywords
- Classification algorithm, Prediction accuracy, Test Set, Text-To-Speech(TTS), linguistic features, prediction model, sentence-final intonation, speech act, speech synthesis, structured classification, training set