Speech Recognition: What's Left?

• Item type: SIG Technical Reports(1)
• 公開日: 2018-10-03
• タイトル: Speech Recognition: What's Left?
• タイトル / 言語: en
• タイトル: Speech Recognition: What's Left?
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 招待講演2
• 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: IBM T. J. Watson Research Center
• 著者所属(英): en
• 著者所属(英): IBM T. J. Watson Research Center
• 著者名: Michael, Picheny
• 著者名(英): Michael, Picheny
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Recent speech recognition advances on the SWITCHBOARD corpus suggest that because of recent advances in Deep Learning, we now achieve Word Error Rates comparable to human listeners. Does this mean the speech recognition problem is solved and the community can move on to a different set of problems? In this talk, we examine speech recognition issues that still plague the community and compare and contrast them to what is known about human perception. We specifically highlight issues in accented speech, noisy / reverberant speech, speaking style, rapid adaptation to new domains, and multilingual speech recognition. We try to demonstrate that compared to human perception, there is still much room for improvement, so significant work in speech recognition research is still required from the community.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Recent speech recognition advances on the SWITCHBOARD corpus suggest that because of recent advances in Deep Learning, we now achieve Word Error Rates comparable to human listeners. Does this mean the speech recognition problem is solved and the community can move on to a different set of problems? In this talk, we examine speech recognition issues that still plague the community and compare and contrast them to what is known about human perception. We specifically highlight issues in accented speech, noisy / reverberant speech, speaking style, rapid adaptation to new domains, and multilingual speech recognition. We try to demonstrate that compared to human perception, there is still much room for improvement, so significant work in speech recognition research is still required from the community.
• 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 2018-SLP-124, 号 7, p. 1-1, 発行日 2018-10-03
• 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