Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task

Komei Sugiura; Naoto Iwahashi; Hideki Kashioka; Satoshi Nakamura

Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task

Komei Sugiura, Naoto Iwahashi, Hideki Kashioka, Satoshi Nakamura

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper proposes a method that generates motions and utterances in an object manipulation dialogue task. The proposed method integrates belief modules for speech, vision, and motions into a probabilistic framework so that a user's utterances can be understood based on multimodal information. Responses to the utterances are optimized based on an integrated confidence measure function for the integrated belief modules. Bayesian logistic regression is used for the learning of the confidence measure function. The experimental results revealed that the proposed method reduced the failure rate from 12% down to 2.6% while the rejection rate was less than 24%.

Original language	English
Pages (from-to)	2483-2486
Number of pages	4
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication status	Published - 2009 Nov 26
Externally published	Yes
Event	10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom Duration: 2009 Sept 6 → 2009 Sept 10

Keywords

Bayesian logistic regression
Confidence
Multimodal spoken dialogue system
Robot language acquisition

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing
Software
Sensory Systems

Cite this

Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task. / Sugiura, Komei; Iwahashi, Naoto; Kashioka, Hideki et al.

In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 26.11.2009, p. 2483-2486.

Research output: Contribution to journal › Conference article › peer-review

@article{58d93889d1684ab6a7d73a75eafafab8,

title = "Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task",

abstract = "This paper proposes a method that generates motions and utterances in an object manipulation dialogue task. The proposed method integrates belief modules for speech, vision, and motions into a probabilistic framework so that a user's utterances can be understood based on multimodal information. Responses to the utterances are optimized based on an integrated confidence measure function for the integrated belief modules. Bayesian logistic regression is used for the learning of the confidence measure function. The experimental results revealed that the proposed method reduced the failure rate from 12% down to 2.6% while the rejection rate was less than 24%.",

keywords = "Bayesian logistic regression, Confidence, Multimodal spoken dialogue system, Robot language acquisition",

author = "Komei Sugiura and Naoto Iwahashi and Hideki Kashioka and Satoshi Nakamura",

year = "2009",

month = nov,

day = "26",

language = "English",

pages = "2483--2486",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

note = "10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 ; Conference date: 06-09-2009 Through 10-09-2009",

}

TY - JOUR

T1 - Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task

AU - Sugiura, Komei

AU - Iwahashi, Naoto

AU - Kashioka, Hideki

AU - Nakamura, Satoshi

PY - 2009/11/26

Y1 - 2009/11/26

N2 - This paper proposes a method that generates motions and utterances in an object manipulation dialogue task. The proposed method integrates belief modules for speech, vision, and motions into a probabilistic framework so that a user's utterances can be understood based on multimodal information. Responses to the utterances are optimized based on an integrated confidence measure function for the integrated belief modules. Bayesian logistic regression is used for the learning of the confidence measure function. The experimental results revealed that the proposed method reduced the failure rate from 12% down to 2.6% while the rejection rate was less than 24%.

AB - This paper proposes a method that generates motions and utterances in an object manipulation dialogue task. The proposed method integrates belief modules for speech, vision, and motions into a probabilistic framework so that a user's utterances can be understood based on multimodal information. Responses to the utterances are optimized based on an integrated confidence measure function for the integrated belief modules. Bayesian logistic regression is used for the learning of the confidence measure function. The experimental results revealed that the proposed method reduced the failure rate from 12% down to 2.6% while the rejection rate was less than 24%.

KW - Bayesian logistic regression

KW - Confidence

KW - Multimodal spoken dialogue system

KW - Robot language acquisition

UR - http://www.scopus.com/inward/record.url?scp=70450174803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450174803&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:70450174803

SN - 2308-457X

SP - 2483

EP - 2486

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009

Y2 - 6 September 2009 through 10 September 2009

ER -

Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this