User Modeling on Temporal Changes in User Behaviors for Spoken Dialogue Systems

2010 Fiscal Year Final Research Report

• Project/Area Number: 21700164
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Intelligent informatics
• Research Institution: Nagoya University (2010); Kyoto University (2009)
• Principal Investigator: KOMATANI Kazunori Nagoya University, 工学研究科, 准教授 (40362579)
• Project Period (FY): 2009 – 2010
• Keywords: 音声対話システム / ユーザモデリング / 経時的変化 / 音声認識 / 習熟度 / バージイン / 信頼度 / 発話タイミング

Research Abstract

We quantitatively modeled users' habituation to a spoken dialogue system by focusing on temporal changes in user behaviors measured by automatic speech recognition (ASR) accuracy and barge-in rates. This model on changing user behaviors can be used as a fundamental finding for realizing user-adaptive interactions. The model is applicable to spoken dialogue systems that generate adaptive responses and select correct ASR results from those that may contain errors. We showed its effectiveness by the improvement of selection accuracy for barge-in utterances.

Research Products

• [Journal Article] A multi-expert model for dialogue and behavior control of conversational robots and agents. (2011)
  • Author(s): Mikio Nakano, Yuji Hasegawa, Kotaro Funakoshi, Johane Takeuchi, Toyotaka Torii, Kazuhiro Nakadai, Naoyuki Kanda, Kazunori Komatani, Hiroshi G Okuno, Hiroshi Tsujino
  • Journal Title: Knowledge-Based Systems Vol.24, Issue 2 Pages: 248-256
  • Peer Reviewed
• [Journal Article] Selecting Help Messages by using Robust Grammar Verification for Handling Out-of-Grammar Utterances in Spoken Dialogue Systems. (2010)
  • Author(s): Kazunori Komatani, Yuichiro Fukubayashi, Satoshi Ikeda, Tetsuya Ogata, Hiroshi G. Okuno
  • Journal Title: IEICE Transactions on Information and Systems Vol.E93-D, No.12 Pages: 3359-3367
  • Peer Reviewed
• [Journal Article] 複数の言語モデルと言語理解モデルによる音声理解の高精度化 (2010)
  • Author(s): 勝丸真樹, 中野幹生, 駒谷和範, 船越孝太郎, 辻野広司, 尾形哲也, 奥乃博
  • Journal Title: 電子情報通信学会論文誌 Vol.J93-D, No.6 Pages: 879-888
  • Peer Reviewed
• [Presentation] 音声対話システムにおけるバージイン発話の分類とそれに基づくエラー検出 (2011)
  • Author(s): 中島大一, 駒谷和範, 佐藤理史
  • Organizer: 言語処理学会第17回年次大会講演論文集
  • Place of Presentation: 豊橋技術科学大学(愛知県)
  • Year and Date: 2011-03-08
• [Presentation] 発語行為レベルの情報を活用した音声対話システムの研究 (2010)
  • Author(s): 駒谷和範, 松山匡子, 奥乃博
  • Organizer: 人工知能学会研究会資料,SIG-SLUD-B002-12, pp.53-58
  • Place of Presentation: 早稲田大学(東京都)
  • Year and Date: 2010-10-28
• [Presentation] Online Error Detection of Barge-In Utterances by Using Individual Users' Utterance Histories in Spoken Dialogue System. (2010)
  • Author(s): Kazunori Komatani, Hiroshi G.Okuno
  • Organizer: 11th Annual SIGDIAL Meeting on Discourse and Dialogue, pp.289-296
  • Place of Presentation: 東京大学(東京都)
  • Year and Date: 2010-09-25
• [Presentation] 音声対話システムにおける各ユーザの利用履歴を活用したバージイン発話のエラー検出 (2010)
  • Author(s): 駒谷和範, 奥乃博
  • Organizer: 言語処理学会第16回年次大会講演論文集 pp.218-221
  • Place of Presentation: 東京大学(東京都)
  • Year and Date: 2010-03-09
• [Presentation] 音声対話システムにおける暗黙的な教師信号に基づく音声認識率の推定とそれを用いたエラー予測 (2009)
  • Author(s): 駒谷和範, Alexander I.Rudnicky
  • Organizer: 情報処理学会研究報告,2009-SLP-78-3
  • Place of Presentation: 早稲田大学(東京都)
  • Year and Date: 2009-10-23
• [Presentation] Predicting Barge-in Utterance Errors by using Implicitly-Supervised ASR Accuracy and Barge-in Rate per User. (2009)
  • Author(s): Kazunori Komatani, Alexander I.Rudnicky
  • Organizer: ACL-IJCNLP 09, Short Papers, pp.89-92
  • Place of Presentation: Singapore(Singapore)
  • Year and Date: 2009-08-04
• [Presentation] A Model of Temporally Changing User Behaviors in a Deployed Spoken Dialogue System. (2009)
  • Author(s): Kazunori Komatani, Tatsuya Kawahara, 奥乃博
  • Organizer: International Conference on User Modeling, Adaptation, and Personalization (UMAP09), LNCS 5535, pp.409-414
  • Place of Presentation: Trento(Italy)
  • Year and Date: 2009-06-23
• [Remarks] ホームページ等
  • URL: http://sslab.nuee.nagoya-u.ac.jp/~komatani/