Prosody control for speaking and singing styles

By proper control of prosody, text-to-speech systems already have the capacity to imitate distinctive speaking styles. We show two examples where we can capture the critical features: the singing style of Dinah Shore and the speaking style of Martin Luther King Jr. The styles are described by Stem-M...

Full description

Bibliographic Details
Main Authors: Shih, C, Kochanski, G
Format: Journal article
Language:English
Published: International Speech Communication Association (ISCA) 2001
Subjects:
_version_ 1826285299661012992
author Shih, C
Kochanski, G
author_facet Shih, C
Kochanski, G
author_sort Shih, C
collection OXFORD
description By proper control of prosody, text-to-speech systems already have the capacity to imitate distinctive speaking styles. We show two examples where we can capture the critical features: the singing style of Dinah Shore and the speaking style of Martin Luther King Jr. The styles are described by Stem-ML tags (soft template mark-up language), which offers the flexibility needed to control accent shapes, phrasal pitch contours, and amplitude profiles, for speech as well as for singing.
first_indexed 2024-03-07T01:26:45Z
format Journal article
id oxford-uuid:923c502c-5c4b-47af-9db9-e72f9db42e94
institution University of Oxford
language English
last_indexed 2024-03-07T01:26:45Z
publishDate 2001
publisher International Speech Communication Association (ISCA)
record_format dspace
spelling oxford-uuid:923c502c-5c4b-47af-9db9-e72f9db42e942022-03-26T23:24:02ZProsody control for speaking and singing stylesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:923c502c-5c4b-47af-9db9-e72f9db42e94LinguisticsEnglishOxford University Research Archive - ValetInternational Speech Communication Association (ISCA)2001Shih, CKochanski, GBy proper control of prosody, text-to-speech systems already have the capacity to imitate distinctive speaking styles. We show two examples where we can capture the critical features: the singing style of Dinah Shore and the speaking style of Martin Luther King Jr. The styles are described by Stem-ML tags (soft template mark-up language), which offers the flexibility needed to control accent shapes, phrasal pitch contours, and amplitude profiles, for speech as well as for singing.
spellingShingle Linguistics
Shih, C
Kochanski, G
Prosody control for speaking and singing styles
title Prosody control for speaking and singing styles
title_full Prosody control for speaking and singing styles
title_fullStr Prosody control for speaking and singing styles
title_full_unstemmed Prosody control for speaking and singing styles
title_short Prosody control for speaking and singing styles
title_sort prosody control for speaking and singing styles
topic Linguistics
work_keys_str_mv AT shihc prosodycontrolforspeakingandsingingstyles
AT kochanskig prosodycontrolforspeakingandsingingstyles