Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts

Takashi Nose; Yusuke Arao; Takao Kobayashi; Komei Sugiura; Yoshinori Shiga; Akinori Ito

Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts

Takashi Nose, Yusuke Arao, Takao Kobayashi, Komei Sugiura, Yoshinori Shiga, Akinori Ito

ENG - Communications Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

Abstract

This paper proposes a sentence selection method using a maxi- mum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech syn- thesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech syn- thesis, phonetic and prosodic contextual balance is important as well as the coverage. To take account of both of the pho- netic and prosodic contextual balance in the sentence selection, we introduce and maximize the entropy of the phonetic and prosodic contexts, such as biphone, triphone, accent, and sen- tence length. The objective experimental results show that the proposed method achieves better coverage and balance of con- texts and reduces spectral and F0 distortions compared to the random and coverage-based sentence selection methods.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publisher	International Speech and Communication Association
Pages	3491-3495
Number of pages	5
Volume	2015-January
Publication status	Published - 2015
Event	16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany Duration: 2015 Sep 6 → 2015 Sep 10

Other

Other	16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015
Country/Territory	Germany
City	Dresden
Period	15/9/6 → 15/9/10

Keywords

Corpus design
Entropy
Sentence selection
Speech synthesis

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts. / Nose, Takashi; Arao, Yusuke; Kobayashi, Takao; Sugiura, Komei; Shiga, Yoshinori; Ito, Akinori.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2015-January International Speech and Communication Association, 2015. p. 3491-3495.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nose, T, Arao, Y, Kobayashi, T, Sugiura, K, Shiga, Y & Ito, A 2015, Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2015-January, International Speech and Communication Association, pp. 3491-3495, 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015, Dresden, Germany, 15/9/6.

Nose, Takashi ; Arao, Yusuke ; Kobayashi, Takao ; Sugiura, Komei ; Shiga, Yoshinori ; Ito, Akinori. / Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2015-January International Speech and Communication Association, 2015. pp. 3491-3495

@inproceedings{6eebf7d5420f4384b77f4688c10ca4c7,

title = "Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts",

abstract = "This paper proposes a sentence selection method using a maxi- mum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech syn- thesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech syn- thesis, phonetic and prosodic contextual balance is important as well as the coverage. To take account of both of the pho- netic and prosodic contextual balance in the sentence selection, we introduce and maximize the entropy of the phonetic and prosodic contexts, such as biphone, triphone, accent, and sen- tence length. The objective experimental results show that the proposed method achieves better coverage and balance of con- texts and reduces spectral and F0 distortions compared to the random and coverage-based sentence selection methods.",

keywords = "Corpus design, Entropy, Sentence selection, Speech synthesis",

author = "Takashi Nose and Yusuke Arao and Takao Kobayashi and Komei Sugiura and Yoshinori Shiga and Akinori Ito",

year = "2015",

language = "English",

volume = "2015-January",

pages = "3491--3495",

booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech and Communication Association",

note = "16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 ; Conference date: 06-09-2015 Through 10-09-2015",

}

TY - GEN

T1 - Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts

AU - Nose, Takashi

AU - Arao, Yusuke

AU - Kobayashi, Takao

AU - Sugiura, Komei

AU - Shiga, Yoshinori

AU - Ito, Akinori

PY - 2015

Y1 - 2015

N2 - This paper proposes a sentence selection method using a maxi- mum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech syn- thesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech syn- thesis, phonetic and prosodic contextual balance is important as well as the coverage. To take account of both of the pho- netic and prosodic contextual balance in the sentence selection, we introduce and maximize the entropy of the phonetic and prosodic contexts, such as biphone, triphone, accent, and sen- tence length. The objective experimental results show that the proposed method achieves better coverage and balance of con- texts and reduces spectral and F0 distortions compared to the random and coverage-based sentence selection methods.

AB - This paper proposes a sentence selection method using a maxi- mum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech syn- thesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech syn- thesis, phonetic and prosodic contextual balance is important as well as the coverage. To take account of both of the pho- netic and prosodic contextual balance in the sentence selection, we introduce and maximize the entropy of the phonetic and prosodic contexts, such as biphone, triphone, accent, and sen- tence length. The objective experimental results show that the proposed method achieves better coverage and balance of con- texts and reduces spectral and F0 distortions compared to the random and coverage-based sentence selection methods.

KW - Corpus design

KW - Entropy

KW - Sentence selection

KW - Speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=84959117873&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959117873&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84959117873

VL - 2015-January

SP - 3491

EP - 3495

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

PB - International Speech and Communication Association

T2 - 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015

Y2 - 6 September 2015 through 10 September 2015

ER -

Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this