話者の印象を考慮した階層的識別器を持つGANによる音声合成

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2020/11/01

タイトル(英語): Speech Synthesis based on Speaker Impression with Hierarchical Discriminator GAN

著者名: 森　優斗（大阪府立大学大学院 工学研究科），井上　勝文（大阪府立大学大学院 工学研究科），吉岡　理文（大阪府立大学大学院 工学研究科）

著者名(英語): Yuto Mori (Graduate School of Engineering, Osaka Prefecture University), Katsufumi Inoue (Graduate School of Engineering, Osaka Prefecture University), Michifumi Yoshioka (Graduate School of Engineering, Osaka Prefecture University)

キーワード: テキスト音声合成，敵対的学習，印象ベクトル　　text-to-speech，Generative Adversarial Network (GAN)，impression vector

要約(英語): Recently, speech synthesis has been spotlighted as a key technology for broadcasting original movie with character on YouTube. To make a natural speech in the methods based on GAN(Generative Adversarial Network), the following unsolved problems are remained: impression of synthesized speech such as warm, cool, etc., and long-term optimization of speech synthesis. In the former problem, since the conventional methods have focused on natural intonation of speech, they have not discussed the impression sufficiently. In this research, to deal with the impression, we proposed a new GAN based speech synthesis method using impression vector digitized the speaker impression. On the other hand, for the latter problem, since conventional methods optimize the relationship among frames insufficiently, the synthesized speech is still not natural. To solve this problem, inspired by an image synthesis technology such as HDGAN, we proposed a new GAN based network structure. The characteristic point is hierarchically nested discriminators at intermediate layers of the generator. In experiments with 15 speeches synthesized by the proposed method and 14 impression items, we estimated impression recognition accuracy by 11 listeners as subjective evaluation. From the experimental results, we have achieved 40.61% of subjective accuracy.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.140 No.11 （2020） 特集：電気関係学会関西連合大会

本誌掲載ページ: 1207-1212 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/140/11/140_1207/_article/-char/ja/