The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
대화 음성 합성에서 모델 적응의 효율성을 탐구합니다. 제안된 적응 방법은 대규모 데이터 세트로 학습된 기본 모델을 대상 대화 스타일 음성 모델로 변환하는 것을 기반으로 합니다. 제안된 방법은 대화의 발화 스타일을 유지하면서 합성된 대화 음성의 명료도를 향상시키는 것으로 나타났습니다.
Kazuki KAYA
Utsunomiya University
Hiroki MORI
Utsunomiya University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Kazuki KAYA, Hiroki MORI, "Effectiveness of Speech Mode Adaptation for Improving Dialogue Speech Synthesis" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 10, pp. 2064-2066, October 2019, doi: 10.1587/transinf.2019EDL8024.
Abstract: The effectiveness of model adaptation in dialogue speech synthesis is explored. The proposed adaptation method is based on a conversion from a base model learned with a large dataset into a target, dialogue-style speech model. The proposed method is shown to improve the intelligibility of synthesized dialogue speech, while maintaining the speaking style of dialogue.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8024/_p
부
@ARTICLE{e102-d_10_2064,
author={Kazuki KAYA, Hiroki MORI, },
journal={IEICE TRANSACTIONS on Information},
title={Effectiveness of Speech Mode Adaptation for Improving Dialogue Speech Synthesis},
year={2019},
volume={E102-D},
number={10},
pages={2064-2066},
abstract={The effectiveness of model adaptation in dialogue speech synthesis is explored. The proposed adaptation method is based on a conversion from a base model learned with a large dataset into a target, dialogue-style speech model. The proposed method is shown to improve the intelligibility of synthesized dialogue speech, while maintaining the speaking style of dialogue.},
keywords={},
doi={10.1587/transinf.2019EDL8024},
ISSN={1745-1361},
month={October},}
부
TY - JOUR
TI - Effectiveness of Speech Mode Adaptation for Improving Dialogue Speech Synthesis
T2 - IEICE TRANSACTIONS on Information
SP - 2064
EP - 2066
AU - Kazuki KAYA
AU - Hiroki MORI
PY - 2019
DO - 10.1587/transinf.2019EDL8024
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2019
AB - The effectiveness of model adaptation in dialogue speech synthesis is explored. The proposed adaptation method is based on a conversion from a base model learned with a large dataset into a target, dialogue-style speech model. The proposed method is shown to improve the intelligibility of synthesized dialogue speech, while maintaining the speaking style of dialogue.
ER -