Implementation and Evaluation of a Multimodal Addressee Identification Mechanism for Multiparty Conversation Systems

被引：8

作者：

Nakano, Yukiko I. ^{[1
]}

Baba, Naoya ^{[1
]}

Huang, Hung-Hsuan ^{[2
]}

Hayashi, Yuki ^{[1
]}

机构：

[1] Seikei Univ, 3-3-1 Kichijoji Kitamachi, Musashino, Tokyo 1808633, Japan

[2] Ritsumeikan Univ, Kusatsu, Shiga 5258577, Japan

来源：

ICMI'13: PROCEEDINGS OF THE 2013 ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION | 2013年

关键词：

Design; Experimentation; Human Factors; Addressee identification; multiparty conversation systems; autonomous virtual agent; evaluation;

D O I：

10.1145/2522848.2522872

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In conversational agents with multiparty communication functionality, a system needs to be able to identify the addressee for the current floor and respond to the user when the utterance is addressed to the agent. This study proposes some addressee identification models based on speech and gaze information, and tests whether the models can be applied to different proxemics. We build an addressee identification mechanism by implementing the models and incorporate it into a fully autonomous multiparty conversational agent. The system identifies the addressee from online multimodal data and uses this information in language understanding and dialogue management. Finally, an evaluation experiment shows that the proposed addressee identification mechanism works well in a real-time system, with an F-measure for addressee estimation of 0.8 for agent-addressed utterances. We also found that our system more successfully avoided disturbing the conversation by mistakenly taking a turn when the agent is not addressed.

引用

页码：35 / 42

页数：8

共 20 条

[1]

Akker R.O.D., 2009, 13 WORKSH SEM PRAGM

[2]

[Anonymous], 2006, PROC 8 INT C MULTIMO, DOI DOI 10.1145/1180995.1181002

[3]

[Anonymous], 2008, 7 INT JOINT C AUTONO, V1, P128

[4]

[Anonymous], 8 INT C INT VIRT AG

[5]

Bakx I., 2003, Human-Comput. Interact, P701

[6]

Bohus D., 2010, ICMI MLMI 10

[7]

Bohus D., 2011, P SIGDIAL 2011 C, P98

[8]

Bohus D., 2009, ICMI MLMI 09

[9]

Chen L., 2009, ICMI MLMI 09

[10] Praat script to detect syllable nuclei and measure speech rate automatically [J].

de Jong, Nivja H. ;

Wempe, Ton .

BEHAVIOR RESEARCH METHODS, 2009, 41 (02) :385-390

← 1 2 →