Improving Intelligibility of Synthesized Speech in Noisy Condition with Dynamically Adaptive Machine Speech Chain

• Item type: SIG Technical Reports(1)
• 公開日: 2021-11-24
• タイトル: Improving Intelligibility of Synthesized Speech in Noisy Condition with Dynamically Adaptive Machine Speech Chain
• タイトル / 言語: en
• タイトル: Improving Intelligibility of Synthesized Speech in Noisy Condition with Dynamically Adaptive Machine Speech Chain
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 音声合成
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属: Japan Advanced Institute of Science and Technology／Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属: Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Japan Advanced Institute of Science and Technology / Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP
• 著者名: Sashi, Novitasari; Sakriani, Sakti; Satoshi, Nakamura
• 著者名(英): Sashi, Novitasari; Sakriani, Sakti; Satoshi, Nakamura
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper focuses on the machine speech chain mechanism for improving the intelligibility of synthesized speech in noisy conditions. Our proposed text-to-speech synthesis (TTS) system synthesizes a speech by adapting to the situation. It will speak with a Lombard effect and high intelligibility in noisy conditions by processing auditory feedback that consists of speech-to-signal ratio (SNR) and automatic speech recognition (ASR) system loss. Our experiments show that auditory feedback improves TTS intelligibility in noisy environments.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper focuses on the machine speech chain mechanism for improving the intelligibility of synthesized speech in noisy conditions. Our proposed text-to-speech synthesis (TTS) system synthesizes a speech by adapting to the situation. It will speak with a Lombard effect and high intelligibility in noisy conditions by processing auditory feedback that consists of speech-to-signal ratio (SNR) and automatic speech recognition (ASR) system loss. Our experiments show that auditory feedback improves TTS intelligibility in noisy environments.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10442647
• 書誌情報: 研究報告音声言語情報処理（SLP）; 巻 2021-SLP-139, 号 24, p. 1-2, 発行日 2021-11-24
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8663
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会