WEKO3
アイテム
An improved minimum generation error based model adaptation for HMM-based speech synthesis
https://nitech.repo.nii.ac.jp/records/3456
https://nitech.repo.nii.ac.jp/records/3456ff2da84c-d7e0-4e2f-ba09-ccad03a8e3e4
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
本文_fulltext (282.7 kB)
|
|
| Item type | 会議発表論文 / Conference Paper(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2012-11-07 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | An improved minimum generation error based model adaptation for HMM-based speech synthesis | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||||||||||
| 資源タイプ | conference paper | |||||||||||||
| 著者 |
Wu, Yi-Jian
× Wu, Yi-Jian
× Qin, Long
|
|||||||||||||
| 著者別名 | ||||||||||||||
| 識別子Scheme | WEKO | |||||||||||||
| 識別子 | 464 | |||||||||||||
| 識別子Scheme | NRID | |||||||||||||
| 識別子URI | http://rns.nii.ac.jp/nr/1000020217483 | |||||||||||||
| 識別子 | 1000020217483 | |||||||||||||
| 姓名 | Tokuda, Keiichi | |||||||||||||
| 言語 | en | |||||||||||||
| 姓名 | 徳田, 恵一 | |||||||||||||
| 言語 | ja | |||||||||||||
| 姓名 | トクダ, ケイイチ | |||||||||||||
| 言語 | ja-Kana | |||||||||||||
| 姓 | Tokuda | |||||||||||||
| 言語 | en | |||||||||||||
| 姓 | 徳田 | |||||||||||||
| 言語 | ja | |||||||||||||
| 姓 | トクダ | |||||||||||||
| 言語 | ja-Kana | |||||||||||||
| 名 | Keiichi | |||||||||||||
| 言語 | en | |||||||||||||
| 名 | 恵一 | |||||||||||||
| 言語 | ja | |||||||||||||
| 名 | ケイイチ | |||||||||||||
| 言語 | ja-Kana | |||||||||||||
| 書誌情報 |
en : INTERSPEECH 2009 10th Annual Conference of the International Speech Communication Association p. 1787-1790, 発行日 2010-08-31 |
|||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | International Speech Communication Association | |||||||||||||
| 言語 | en | |||||||||||||
| 著者版フラグ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| 内容記述 | ||||||||||||||
| 内容記述タイプ | Other | |||||||||||||
| 内容記述 | Aminimum generation error (MGE) criterion had been proposedfor model training in HMM-based speech synthesis. Inthis paper, we apply the MGE criterion to model adaptation forHMM-based speech synthesis, and introduce an MGE linear regression(MGELR) based model adaptation algorithm, wherethe regression matrices used to transform source models are optimizedso as to minimize the generation errors of adaptationdata. In addition, we incorporate the recent improvements ofMGE criterion into MGELR-based model adaptation, includingstate alignment under MGE criterion and using a log spectraldistortion (LSD) instead of Euclidean distance for spectraldistortion measure. From the experimental results, the adaptationperformance was improved after incorporating these twotechniques, and the formal listening tests showed that the qualityand speaker similarity of synthesized speech after MGELRbasedadaptation were significantly improved over the originalMLLR-based adaptation. | |||||||||||||
| 言語 | en | |||||||||||||
| 内容記述 | ||||||||||||||
| 内容記述タイプ | Other | |||||||||||||
| 内容記述 | Brighton, United KingdomSeptember 6-10, 2009 | |||||||||||||
| 言語 | en | |||||||||||||
| 関連サイト | ||||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 関連識別子 | http://www.isca-speech.org/archive/interspeech_2009/i09_1787.html | |||||||||||||
| 関連名称 | http://www.isca-speech.org/archive/interspeech_2009/i09_1787.html | |||||||||||||
