Modeling of vocal styles using portable features and placement rules
We present a step towards a mathematical description of style in speech and singing. We represent a style of speech or singing as a set of portable prosodic features along with a set of rules to choose where the features are to be applied. Speech and singing can both be conveniently described by sep...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer
2003
|
| Subjects: |
| _version_ | 1826271959970742272 |
|---|---|
| author | Shih, C Kochanski, G |
| author_facet | Shih, C Kochanski, G |
| author_sort | Shih, C |
| collection | OXFORD |
| description | We present a step towards a mathematical description of style in speech and singing. We represent a style of speech or singing as a set of portable prosodic features along with a set of rules to choose where the features are to be applied. Speech and singing can both be conveniently described by separating their style from their content. In both speech and singing, style is implemented in terms of acoustic parameters like pitch and loudness. The features we use correspond to musical embellishments or prosodic accents and phrase curve in speech, and are implemented via Stem-ML (Soft TEMplate Mark-up Language). We present several examples to illustrate the usefulness of the style/content separation, and the similarity between speech and music. |
| first_indexed | 2024-03-06T22:04:58Z |
| format | Journal article |
| id | oxford-uuid:4fd36546-eebb-4d75-b7d5-f33886c84ea1 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:04:58Z |
| publishDate | 2003 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:4fd36546-eebb-4d75-b7d5-f33886c84ea12022-03-26T16:10:00ZModeling of vocal styles using portable features and placement rulesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:4fd36546-eebb-4d75-b7d5-f33886c84ea1LinguisticsComputational LinguisticsEnglishOxford University Research Archive - ValetSpringer2003Shih, CKochanski, GWe present a step towards a mathematical description of style in speech and singing. We represent a style of speech or singing as a set of portable prosodic features along with a set of rules to choose where the features are to be applied. Speech and singing can both be conveniently described by separating their style from their content. In both speech and singing, style is implemented in terms of acoustic parameters like pitch and loudness. The features we use correspond to musical embellishments or prosodic accents and phrase curve in speech, and are implemented via Stem-ML (Soft TEMplate Mark-up Language). We present several examples to illustrate the usefulness of the style/content separation, and the similarity between speech and music. |
| spellingShingle | Linguistics Computational Linguistics Shih, C Kochanski, G Modeling of vocal styles using portable features and placement rules |
| title | Modeling of vocal styles using portable features and placement rules |
| title_full | Modeling of vocal styles using portable features and placement rules |
| title_fullStr | Modeling of vocal styles using portable features and placement rules |
| title_full_unstemmed | Modeling of vocal styles using portable features and placement rules |
| title_short | Modeling of vocal styles using portable features and placement rules |
| title_sort | modeling of vocal styles using portable features and placement rules |
| topic | Linguistics Computational Linguistics |
| work_keys_str_mv | AT shihc modelingofvocalstylesusingportablefeaturesandplacementrules AT kochanskig modelingofvocalstylesusingportablefeaturesandplacementrules |