| 講演名 | 2016-03-29 [Poster Presentation] Quality improvement of HMM-based synthesized speech based on decomposition of naturalness and intelligibility using asymmetric bilinear model with non-negative matrix factorization Anh-Tuan Dinh(北陸先端大), Masato Akagi(北陸先端大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | HMM-based synthesized voices are intelligible but not natural especially in limited data condition because of over-smoothing speech spectra. One solution for the problem is using voice conversion techniques to convert over-smoothed spectra to natural spectra. Although conventional conversion techniques transform speech spectra to natural ones to improve naturalness, they cause unexpected distortions on acceptable intelligibility of synthesized speech. The aim of this paper is to improve naturalness without violating acceptable intelligibility employing a novel asymmetric bi-linear model (ABM) using non-negative matrix factorization (NMF) to separate the naturalness and intelligibility of synthesized speech. Subjective evaluations carried out on English data confirm that the achieved synthesis quality is higher than other methods in limited data condition and competitive in large data condition. Moreover, non-negativity constrain in NMF helps reveal the physical meanings of factored matrices as naturalness and intelligibility. |
| 抄録(英) | HMM-based synthesized voices are intelligible but not natural especially in limited data condition because of over-smoothing speech spectra. One solution for the problem is using voice conversion techniques to convert over-smoothed spectra to natural spectra. Although conventional conversion techniques transform speech spectra to natural ones to improve naturalness, they cause unexpected distortions on acceptable intelligibility of synthesized speech. The aim of this paper is to improve naturalness without violating acceptable intelligibility employing a novel asymmetric bi-linear model (ABM) using non-negative matrix factorization (NMF) to separate the naturalness and intelligibility of synthesized speech. Subjective evaluations carried out on English data confirm that the achieved synthesis quality is higher than other methods in limited data condition and competitive in large data condition. Moreover, non-negativity constrain in NMF helps reveal the physical meanings of factored matrices as naturalness and intelligibility. |
| キーワード(和) | HMM-based speech synthesis / asymmetric bi-linear model / non-negative matrix factorization / decompostion of naturalness and intelligibility / naturalness improvement |
| キーワード(英) | HMM-based speech synthesis / asymmetric bi-linear model / non-negative matrix factorization / decompostion of naturalness and intelligibility / naturalness improvement |
| 資料番号 | EA2015-113,SIP2015-162,SP2015-141 |
| 発行日 | 2016-03-21 (EA, SIP, SP) |
| 研究会情報 | |
| 研究会 | EA / SP / SIP |
|---|---|
| 開催期間 | 2016/3/28(から2日開催) |
| 開催地（和） | 別府国際コンベンションセンター B-ConPlaza |
| 開催地（英） | Beppu International Convention Center B-ConPlaza |
| テーマ（和） | 応用／電気音響，音声，信号処理，一般 |
| テーマ（英） | Engineering/Electro Acoustics, Speech, Signal Processing, and Related Topics |
| 委員長氏名（和） | 羽田 陽一(電通大) / 間野 一則(芝浦工大) / 宝珠山 治(NEC) |
| 委員長氏名（英） | Yoichi Haneda(Univ. of Electro-Comm.) / Kazunori Mano(Shibaura Inst. of Tech.) / Osamu Houshuyama(NEC) |
| 副委員長氏名（和） | 岩谷 幸雄(東北学院大) / 水町 光徳(九工大) / 北岡 教英(徳島大) / 中静 真(千葉工大) / 奥田 正浩(北九州市大) |
| 副委員長氏名（英） | Yukio Iwaya(Tohoku Gakuin Univ.) / Mitsunori Mizumachi(Kyushu Inst. of Tech.) / Norihide Kitaoka(Tokushima Univ.) / Makoto Nakashizuka(Chiba Inst. of Tech.) / Masahiro Okuda(Univ. of Kitakyushu) |
| 幹事氏名（和） | 島内 末廣(NTT) / 堀内 俊治(KDDI研) / 岩野 公司(東京都市大) / 滝口 哲也(神戸大) / 辻川 剛範(NEC) / 平林 晃(立命館大) |
| 幹事氏名（英） | Suehiro Shimauchi(NTT) / Toshiharu Horiuchi(KDDI R&D Labs.) / Koji Iwano(Tokyo City Univ.) / Tetsuya Takiguchi(Kobe Univ.) / Masanori Tsujikawa(NEC) / Akira Hirabayashi(Ritsumeikan Univ.) |
| 幹事補佐氏名（和） | 小山 翔一(東大) / 能勢 隆(東北大) / 浅見 太一(NTT) / 宮田 高道(千葉工大) |
| 幹事補佐氏名（英） | Shoichi Koyama(Univ. of Tokyo) / Takashi Nose(Tohoku Univ.) / Taichi Asami(NTT) / Takamichi Miyata(Chiba Inst. of Tech.) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Engineering Acoustics / Technical Committee on Speech / Technical Committee on Signal Processing |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | [Poster Presentation] Quality improvement of HMM-based synthesized speech based on decomposition of naturalness and intelligibility using asymmetric bilinear model with non-negative matrix factorization |
| サブタイトル（和） | |
| キーワード(1)（和/英） | HMM-based speech synthesis / HMM-based speech synthesis |
| キーワード(2)（和/英） | asymmetric bi-linear model / asymmetric bi-linear model |
| キーワード(3)（和/英） | non-negative matrix factorization / non-negative matrix factorization |
| キーワード(4)（和/英） | decompostion of naturalness and intelligibility / decompostion of naturalness and intelligibility |
| キーワード(5)（和/英） | naturalness improvement / naturalness improvement |
| 第 1 著者 氏名（和/英） | Anh-Tuan Dinh / Anh-Tuan Dinh |
| 第 1 著者 所属（和/英） | Japan Advanced Institute of Science and Technology(略称：北陸先端大) Japan Advanced Institute of Science and Technology(略称：JAIST) |
| 第 2 著者 氏名（和/英） | Masato Akagi / Masato Akagi |
| 第 2 著者 所属（和/英） | Japan Advanced Institute of Science and Technology(略称：北陸先端大) Japan Advanced Institute of Science and Technology(略称：JAIST) |
| 発表年月日 | 2016-03-29 |
| 資料番号 | EA2015-113,SIP2015-162,SP2015-141 |
| 巻番号（vol） | vol.115 |
| 号番号（no） | EA-521,SIP-522,SP-523 |
| ページ範囲 | pp.261-266(EA), pp.261-266(SIP), pp.261-266(SP), |
| ページ数 | 6 |
| 発行日 | 2016-03-21 (EA, SIP, SP) |