| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2016-03-29 09:00 ［ポスター講演］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・Masato Akagi（JAIST）  EA2015-113 SIP2015-162 SP2015-141 |
|
| 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. |
| （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 / / / |
| （英） | HMM-based speech synthesis / asymmetric bi-linear model / non-negative matrix factorization / decompostion of naturalness and intelligibility / naturalness improvement / / / | |
| 文献情報 | 信学技報, vol. 115, no. 523, SP2015-141, pp. 261-266, 2016年3月. | |
| 資料番号 | SP2015-141 | |
| 発行日 | 2016-03-21 (EA, SIP, SP) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | EA2015-113 SIP2015-162 SP2015-141 |
|
| 研究会情報 | |
| 研究会 | EA SP SIP |
| 開催期間 | 2016-03-28 - 2016-03-29 |
| 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 |
| 講演論文情報の詳細 | |
| 申込み研究会 | SP |
| 会議コード | 2016-03-EA-SP-SIP |
| 本文の言語 | 英語 |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | 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（英） | |
| 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 |
| キーワード(6)（和/英） | / |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | 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/ヨミ） | 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) |
| 講演者 | 第1著者 |
| 発表日時 | 2016-03-29 09:00:00 |
| 発表時間 | 90分 |
| 申込先研究会 | SP |
| 資料番号 | EA2015-113, SIP2015-162, SP2015-141 |
| 巻番号（vol） | vol.115 |
| 号番号（no） | no.521(EA), no.522(SIP), no.523(SP) |
| ページ範囲 | pp.261-266 |
| ページ数 | 6 |
| 発行日 | 2016-03-21 (EA, SIP, SP) |
[研究会発表申込システムのトップページに戻る]