A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis

Odétúnjí A. Odéjobí; Anthony J. Beaumont; Shun Ha Sylvia Wong

doi:10.1007/978-3-540-30120-2_52

A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis

Odétúnjí A. Odéjobí, Anthony J. Beaumont, Shun Ha Sylvia Wong

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

In this paper we present the design and analysis of an intonation model for text-to-speech (TTS) synthesis applications using a combination of Relational Tree (RT) and Fuzzy Logic (FL) technologies. The model is demonstrated using the Standard Yorùbá (SY) language. In the proposed intonation model, phonological information extracted from text is converted into an RT. RT is a sophisticated data structure that represents the peaks and valleys as well as the spatial structure of a waveform symbolically in the form of trees. An initial approximation to the RT, called Skeletal Tree (ST), is first generated algorithmically. The exact numerical values of the peaks and valleys on the ST is then computed using FL. Quantitative analysis of the result gives RMSE of 0.56 and 0.71 for peak and valley respectively. Mean Opinion Scores (MOS) of 9.5 and 6.8, on a scale of 1 - -10, was obtained for intelligibility and naturalness respectively.

Original language	English
Title of host publication	Text, speech and dialogue
Subtitle of host publication	7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings
Editors	Petr Sojka, Ivan Kopeček, Karel Pala
Place of Publication	Berlin (DE)
Publisher	Springer
Pages	409-416
Number of pages	8
Volume	Part III
ISBN (Electronic)	978-3-540-30120-2
ISBN (Print)	978-3-540-23049-6
DOIs	https://doi.org/10.1007/978-3-540-30120-2_52
Publication status	Published - 2004

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	3206
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Access to Document

10.1007/978-3-540-30120-2_52

Cite this

Odéjobí, O. A., Beaumont, A. J., & Wong, S. H. S. (2004). A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis. In P. Sojka, I. Kopeček, & K. Pala (Eds.), Text, speech and dialogue: 7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings (Vol. Part III, pp. 409-416). (Lecture notes in computer science; Vol. 3206). Springer. https://doi.org/10.1007/978-3-540-30120-2_52

Odéjobí, Odétúnjí A. ; Beaumont, Anthony J. ; Wong, Shun Ha Sylvia. / A computational model of intonation for yorùbá text-to-speech synthesis : design and analysis. Text, speech and dialogue: 7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings. editor / Petr Sojka ; Ivan Kopeček ; Karel Pala. Vol. Part III Berlin (DE) : Springer, 2004. pp. 409-416 (Lecture notes in computer science).

@inproceedings{49d4296c605e4ce7890c3987c72449c1,

title = "A computational model of intonation for yor{\`u}b{\'a} text-to-speech synthesis: design and analysis",

abstract = "In this paper we present the design and analysis of an intonation model for text-to-speech (TTS) synthesis applications using a combination of Relational Tree (RT) and Fuzzy Logic (FL) technologies. The model is demonstrated using the Standard Yor{\`u}b{\'a} (SY) language. In the proposed intonation model, phonological information extracted from text is converted into an RT. RT is a sophisticated data structure that represents the peaks and valleys as well as the spatial structure of a waveform symbolically in the form of trees. An initial approximation to the RT, called Skeletal Tree (ST), is first generated algorithmically. The exact numerical values of the peaks and valleys on the ST is then computed using FL. Quantitative analysis of the result gives RMSE of 0.56 and 0.71 for peak and valley respectively. Mean Opinion Scores (MOS) of 9.5 and 6.8, on a scale of 1 - -10, was obtained for intelligibility and naturalness respectively.",

author = "Od{\'e}job{\'i}, {Od{\'e}t{\'u}nj{\'i} A.} and Beaumont, {Anthony J.} and Wong, {Shun Ha Sylvia}",

year = "2004",

doi = "10.1007/978-3-540-30120-2_52",

language = "English",

isbn = "978-3-540-23049-6",

volume = "Part III",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "409--416",

editor = "Petr Sojka and Ivan Kope{\v c}ek and Karel Pala",

booktitle = "Text, speech and dialogue",

address = "Germany",

}

Odéjobí, OA, Beaumont, AJ & Wong, SHS 2004, A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis. in P Sojka, I Kopeček & K Pala (eds), Text, speech and dialogue: 7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings. vol. Part III, Lecture notes in computer science, vol. 3206, Springer, Berlin (DE), pp. 409-416. https://doi.org/10.1007/978-3-540-30120-2_52

A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis. / Odéjobí, Odétúnjí A.; Beaumont, Anthony J.; Wong, Shun Ha Sylvia.
Text, speech and dialogue: 7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings. ed. / Petr Sojka; Ivan Kopeček; Karel Pala. Vol. Part III Berlin (DE): Springer, 2004. p. 409-416 (Lecture notes in computer science; Vol. 3206).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - A computational model of intonation for yorùbá text-to-speech synthesis

T2 - design and analysis

AU - Odéjobí, Odétúnjí A.

AU - Beaumont, Anthony J.

AU - Wong, Shun Ha Sylvia

PY - 2004

Y1 - 2004

N2 - In this paper we present the design and analysis of an intonation model for text-to-speech (TTS) synthesis applications using a combination of Relational Tree (RT) and Fuzzy Logic (FL) technologies. The model is demonstrated using the Standard Yorùbá (SY) language. In the proposed intonation model, phonological information extracted from text is converted into an RT. RT is a sophisticated data structure that represents the peaks and valleys as well as the spatial structure of a waveform symbolically in the form of trees. An initial approximation to the RT, called Skeletal Tree (ST), is first generated algorithmically. The exact numerical values of the peaks and valleys on the ST is then computed using FL. Quantitative analysis of the result gives RMSE of 0.56 and 0.71 for peak and valley respectively. Mean Opinion Scores (MOS) of 9.5 and 6.8, on a scale of 1 - -10, was obtained for intelligibility and naturalness respectively.

AB - In this paper we present the design and analysis of an intonation model for text-to-speech (TTS) synthesis applications using a combination of Relational Tree (RT) and Fuzzy Logic (FL) technologies. The model is demonstrated using the Standard Yorùbá (SY) language. In the proposed intonation model, phonological information extracted from text is converted into an RT. RT is a sophisticated data structure that represents the peaks and valleys as well as the spatial structure of a waveform symbolically in the form of trees. An initial approximation to the RT, called Skeletal Tree (ST), is first generated algorithmically. The exact numerical values of the peaks and valleys on the ST is then computed using FL. Quantitative analysis of the result gives RMSE of 0.56 and 0.71 for peak and valley respectively. Mean Opinion Scores (MOS) of 9.5 and 6.8, on a scale of 1 - -10, was obtained for intelligibility and naturalness respectively.

UR - http://www.scopus.com/inward/record.url?scp=22944489587&partnerID=8YFLogxK

UR - http://link.springer.com/chapter/10.1007%2F978-3-540-30120-2_52

U2 - 10.1007/978-3-540-30120-2_52

DO - 10.1007/978-3-540-30120-2_52

M3 - Conference publication

AN - SCOPUS:22944489587

SN - 978-3-540-23049-6

VL - Part III

T3 - Lecture notes in computer science

SP - 409

EP - 416

BT - Text, speech and dialogue

A2 - Sojka, Petr

A2 - Kopeček, Ivan

A2 - Pala, Karel

PB - Springer

CY - Berlin (DE)

ER -

Odéjobí OA, Beaumont AJ, Wong SHS. A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis. In Sojka P, Kopeček I, Pala K, editors, Text, speech and dialogue: 7th international conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004. Proceedings. Vol. Part III. Berlin (DE): Springer. 2004. p. 409-416. (Lecture notes in computer science). doi: 10.1007/978-3-540-30120-2_52

A computational model of intonation for yorùbá text-to-speech synthesis: design and analysis

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this