Prosody modeling with soft templates
This paper describes a novel prosody generation model. We intend it to broadly support many linguistic theories and multiple languages, for the model imposes no restriction on accent categories and shapes. This capability is crucial to the next-generation of Text-to-Speech systems that will need to...
| 主要な著者: | , |
|---|---|
| その他の著者: | |
| フォーマット: | Journal article |
| 言語: | English |
| 出版事項: |
Elsevier
2003
|
| 主題: |
| _version_ | 1826288998342983680 |
|---|---|
| author | Kochanski, G Shih, C |
| author2 | European Association for Signal Processing (EURASIP) |
| author_facet | European Association for Signal Processing (EURASIP) Kochanski, G Shih, C |
| author_sort | Kochanski, G |
| collection | OXFORD |
| description | This paper describes a novel prosody generation model. We intend it to broadly support many linguistic theories and multiple languages, for the model imposes no restriction on accent categories and shapes. This capability is crucial to the next-generation of Text-to-Speech systems that will need to synthesize intonation variations for different speech acts, emotions, and styles of speech. The system supports mark-up tags that are mathematically defined and generate f0 deterministically. Underlying the tags is an articulatory model of accent interaction which balances physiological and communication constraints. We specify the model by way of an algorithm for calculating the pitch, and by way of examples. The model allows localized, linguistically reasonable tags, and is suitable for a data-driven fitting process. |
| first_indexed | 2024-03-07T02:22:12Z |
| format | Journal article |
| id | oxford-uuid:a453b9e5-010e-42e4-b41b-e5b882ad1bc3 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:22:12Z |
| publishDate | 2003 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:a453b9e5-010e-42e4-b41b-e5b882ad1bc32022-03-27T02:33:03ZProsody modeling with soft templatesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:a453b9e5-010e-42e4-b41b-e5b882ad1bc3LinguisticsComputational LinguisticsEnglishOxford University Research Archive - ValetElsevier2003Kochanski, GShih, CEuropean Association for Signal Processing (EURASIP)International Speech Communication AssociationThis paper describes a novel prosody generation model. We intend it to broadly support many linguistic theories and multiple languages, for the model imposes no restriction on accent categories and shapes. This capability is crucial to the next-generation of Text-to-Speech systems that will need to synthesize intonation variations for different speech acts, emotions, and styles of speech. The system supports mark-up tags that are mathematically defined and generate f0 deterministically. Underlying the tags is an articulatory model of accent interaction which balances physiological and communication constraints. We specify the model by way of an algorithm for calculating the pitch, and by way of examples. The model allows localized, linguistically reasonable tags, and is suitable for a data-driven fitting process. |
| spellingShingle | Linguistics Computational Linguistics Kochanski, G Shih, C Prosody modeling with soft templates |
| title | Prosody modeling with soft templates |
| title_full | Prosody modeling with soft templates |
| title_fullStr | Prosody modeling with soft templates |
| title_full_unstemmed | Prosody modeling with soft templates |
| title_short | Prosody modeling with soft templates |
| title_sort | prosody modeling with soft templates |
| topic | Linguistics Computational Linguistics |
| work_keys_str_mv | AT kochanskig prosodymodelingwithsofttemplates AT shihc prosodymodelingwithsofttemplates |