Automatic Estimation of Accentual Attribute Values of Words for Accent Sandhi Rules of Japanese Text-to-Speech Conversion

Nobuaki MINEMATSU; Ryuji KITA; Keikichi HIROSE

Automatic Estimation of Accentual Attribute Values of Words for Accent Sandhi Rules of Japanese Text-to-Speech Conversion

Nobuaki MINEMATSU, Ryuji KITA, Keikichi HIROSE

Full Text Views

0

Cite this

Summary :

Accurate estimation of accentual attribute values of words, which is required to apply rules of Japanese word accent sandhi to prosody generation, is an important factor to realize high-quality text-to-speech (TTS) conversion. The rules were already formulated by Sagisaka et al. and are widely used in Japanese TTS conversion systems. Application of these rules, however, requires values of a few accentual attributes of each constituent word of input text. The attribute values cannot be found in any public database or any accent dictionaries of Japanese. Further, these values are difficult even for native speakers of Japanese to estimate only with their introspective consideration of properties of their mother tongue. In this paper, an algorithm was proposed, where these values were automatically estimated from a large amount of data of accent types of accentual phrases, which were collected through a long series of listening experiments. In the proposed algorithm, inter-speaker differences of knowledge of accent sandhi were well considered. To improve the coverage of the estimated values over the obtained data, the rules were tentatively modified. Evaluation experiments using two-mora accentual phrases showed the high validity of the estimated values and the modified rules and also some defects caused by varieties of linguistic expressions of Japanese.

Publication: IEICE TRANSACTIONS on Information Vol.E86-D No.3 pp.550-557

Publication Date: 2003/03/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Speech Information Processing)

Category: Speech Synthesis and Prosody

Cite this

Copy

Nobuaki MINEMATSU, Ryuji KITA, Keikichi HIROSE, "Automatic Estimation of Accentual Attribute Values of Words for Accent Sandhi Rules of Japanese Text-to-Speech Conversion" in IEICE TRANSACTIONS on Information, vol. E86-D, no. 3, pp. 550-557, March 2003, doi: .
Abstract: Accurate estimation of accentual attribute values of words, which is required to apply rules of Japanese word accent sandhi to prosody generation, is an important factor to realize high-quality text-to-speech (TTS) conversion. The rules were already formulated by Sagisaka et al. and are widely used in Japanese TTS conversion systems. Application of these rules, however, requires values of a few accentual attributes of each constituent word of input text. The attribute values cannot be found in any public database or any accent dictionaries of Japanese. Further, these values are difficult even for native speakers of Japanese to estimate only with their introspective consideration of properties of their mother tongue. In this paper, an algorithm was proposed, where these values were automatically estimated from a large amount of data of accent types of accentual phrases, which were collected through a long series of listening experiments. In the proposed algorithm, inter-speaker differences of knowledge of accent sandhi were well considered. To improve the coverage of the estimated values over the obtained data, the rules were tentatively modified. Evaluation experiments using two-mora accentual phrases showed the high validity of the estimated values and the modified rules and also some defects caused by varieties of linguistic expressions of Japanese.
URL: https://global.ieice.org/en_transactions/information/10.1587/e86-d_3_550/_p

Copy

@ARTICLE{e86-d_3_550,
author={Nobuaki MINEMATSU, Ryuji KITA, Keikichi HIROSE, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Estimation of Accentual Attribute Values of Words for Accent Sandhi Rules of Japanese Text-to-Speech Conversion},
year={2003},
volume={E86-D},
number={3},
pages={550-557},
abstract={Accurate estimation of accentual attribute values of words, which is required to apply rules of Japanese word accent sandhi to prosody generation, is an important factor to realize high-quality text-to-speech (TTS) conversion. The rules were already formulated by Sagisaka et al. and are widely used in Japanese TTS conversion systems. Application of these rules, however, requires values of a few accentual attributes of each constituent word of input text. The attribute values cannot be found in any public database or any accent dictionaries of Japanese. Further, these values are difficult even for native speakers of Japanese to estimate only with their introspective consideration of properties of their mother tongue. In this paper, an algorithm was proposed, where these values were automatically estimated from a large amount of data of accent types of accentual phrases, which were collected through a long series of listening experiments. In the proposed algorithm, inter-speaker differences of knowledge of accent sandhi were well considered. To improve the coverage of the estimated values over the obtained data, the rules were tentatively modified. Evaluation experiments using two-mora accentual phrases showed the high validity of the estimated values and the modified rules and also some defects caused by varieties of linguistic expressions of Japanese.},
keywords={},
doi={},
ISSN={},
month={March},}

Copy

TY - JOUR
TI - Automatic Estimation of Accentual Attribute Values of Words for Accent Sandhi Rules of Japanese Text-to-Speech Conversion
T2 - IEICE TRANSACTIONS on Information
SP - 550
EP - 557
AU - Nobuaki MINEMATSU
AU - Ryuji KITA
AU - Keikichi HIROSE
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2003
AB - Accurate estimation of accentual attribute values of words, which is required to apply rules of Japanese word accent sandhi to prosody generation, is an important factor to realize high-quality text-to-speech (TTS) conversion. The rules were already formulated by Sagisaka et al. and are widely used in Japanese TTS conversion systems. Application of these rules, however, requires values of a few accentual attributes of each constituent word of input text. The attribute values cannot be found in any public database or any accent dictionaries of Japanese. Further, these values are difficult even for native speakers of Japanese to estimate only with their introspective consideration of properties of their mother tongue. In this paper, an algorithm was proposed, where these values were automatically estimated from a large amount of data of accent types of accentual phrases, which were collected through a long series of listening experiments. In the proposed algorithm, inter-speaker differences of knowledge of accent sandhi were well considered. To improve the coverage of the estimated values over the obtained data, the rules were tentatively modified. Evaluation experiments using two-mora accentual phrases showed the high validity of the estimated values and the modified rules and also some defects caused by varieties of linguistic expressions of Japanese.
ER -