Modeling segmental duration in German text-to-speech synthesis

Bernd Mobius, Jan Van Santen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

32 Citations (Scopus)

Abstract

This paper reports on the construction of a model for segmental duration in German. The model predicts the durations of speech sounds in various textual, prosodic, and segmental contexts. It has been implemented in the German version of the Bell Labs text-to-speech system. The construction of the duration system was made efficient by the use of an interactive statistical analysis package that incorporates the approach outlined in [23]. The results are stored in tables in a format that can be directly interpreted by the TTS duration module. Tables are constructed in two phases: inferential-statistical analysis of the speech corpus, and parameter estimation. The overall correlation between observed and predicted segmental durations is .896.

Original languageEnglish (US)
Title of host publicationInternational Conference on Spoken Language Processing, ICSLP, Proceedings
Editors Anon
PublisherIEEE
Pages2395-2398
Number of pages4
Volume4
StatePublished - 1996
Externally publishedYes
EventProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4) - Philadelphia, PA, USA
Duration: Oct 3 1996Oct 6 1996

Other

OtherProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4)
CityPhiladelphia, PA, USA
Period10/3/9610/6/96

Fingerprint

Speech synthesis
Statistical methods
Parameter estimation
Acoustic waves

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Mobius, B., & Van Santen, J. (1996). Modeling segmental duration in German text-to-speech synthesis. In Anon (Ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings (Vol. 4, pp. 2395-2398). IEEE.

Modeling segmental duration in German text-to-speech synthesis. / Mobius, Bernd; Van Santen, Jan.

International Conference on Spoken Language Processing, ICSLP, Proceedings. ed. / Anon. Vol. 4 IEEE, 1996. p. 2395-2398.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mobius, B & Van Santen, J 1996, Modeling segmental duration in German text-to-speech synthesis. in Anon (ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings. vol. 4, IEEE, pp. 2395-2398, Proceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4), Philadelphia, PA, USA, 10/3/96.
Mobius B, Van Santen J. Modeling segmental duration in German text-to-speech synthesis. In Anon, editor, International Conference on Spoken Language Processing, ICSLP, Proceedings. Vol. 4. IEEE. 1996. p. 2395-2398
Mobius, Bernd ; Van Santen, Jan. / Modeling segmental duration in German text-to-speech synthesis. International Conference on Spoken Language Processing, ICSLP, Proceedings. editor / Anon. Vol. 4 IEEE, 1996. pp. 2395-2398
@inproceedings{eb48493739ee481e9fb98b8d98eb79c6,
title = "Modeling segmental duration in German text-to-speech synthesis",
abstract = "This paper reports on the construction of a model for segmental duration in German. The model predicts the durations of speech sounds in various textual, prosodic, and segmental contexts. It has been implemented in the German version of the Bell Labs text-to-speech system. The construction of the duration system was made efficient by the use of an interactive statistical analysis package that incorporates the approach outlined in [23]. The results are stored in tables in a format that can be directly interpreted by the TTS duration module. Tables are constructed in two phases: inferential-statistical analysis of the speech corpus, and parameter estimation. The overall correlation between observed and predicted segmental durations is .896.",
author = "Bernd Mobius and {Van Santen}, Jan",
year = "1996",
language = "English (US)",
volume = "4",
pages = "2395--2398",
editor = "Anon",
booktitle = "International Conference on Spoken Language Processing, ICSLP, Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Modeling segmental duration in German text-to-speech synthesis

AU - Mobius, Bernd

AU - Van Santen, Jan

PY - 1996

Y1 - 1996

N2 - This paper reports on the construction of a model for segmental duration in German. The model predicts the durations of speech sounds in various textual, prosodic, and segmental contexts. It has been implemented in the German version of the Bell Labs text-to-speech system. The construction of the duration system was made efficient by the use of an interactive statistical analysis package that incorporates the approach outlined in [23]. The results are stored in tables in a format that can be directly interpreted by the TTS duration module. Tables are constructed in two phases: inferential-statistical analysis of the speech corpus, and parameter estimation. The overall correlation between observed and predicted segmental durations is .896.

AB - This paper reports on the construction of a model for segmental duration in German. The model predicts the durations of speech sounds in various textual, prosodic, and segmental contexts. It has been implemented in the German version of the Bell Labs text-to-speech system. The construction of the duration system was made efficient by the use of an interactive statistical analysis package that incorporates the approach outlined in [23]. The results are stored in tables in a format that can be directly interpreted by the TTS duration module. Tables are constructed in two phases: inferential-statistical analysis of the speech corpus, and parameter estimation. The overall correlation between observed and predicted segmental durations is .896.

UR - http://www.scopus.com/inward/record.url?scp=0030366723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030366723&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 2395

EP - 2398

BT - International Conference on Spoken Language Processing, ICSLP, Proceedings

A2 - Anon, null

PB - IEEE

ER -