HIERARCHICAL HMM-BASED SEMANTIC CONCEPT LABELING MODEL

被引：1

作者：

Mengistu, Kinfe Tadesse ^{[1
]}

Hannemann, Mirko ^{[1
]}

Baum, Tobias ^{[1
]}

Wendemuth, Andreas ^{[1
]}

机构：

[1] Otto VonGuericke Univ Magdegurg, FEIT IESK, Cognit Syst Grp, D-39106 Magdeburg, Germany

来源：

2008 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY: SLT 2008, PROCEEDINGS | 2008年

关键词：

Hidden Markov model; Hierarchical model; Semantic concept; Spoken language understanding;

D O I：

10.1109/SLT.2008.4777839

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An utterance can be conceived as a hidden sequence of semantic concepts expressed in words or phrases. The problem of understanding the meaning underlying a spoken utterance in a dialog system can be partly solved by decodincy the hidden sequence of semantic concepts from the observed sequence of words. In this paper, we describe a hierarchical HMM-based semantic concept labeling model trained on semantically unlabeled data. The hierarchical model is compared with a flat-concept based model in terms of performance, ambiguity resolution ability and expressive power of the output. It is shown that the proposed method outperforms the flat-concept model in these points.

引用

页码：57 / 60

页数：4

共 50 条

[1] An HMM-based framework for video semantic analysis
Xu, G
Ma, YF
Zhang, HJ
Yang, SQ
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2005, 15 (11) : 1422 - 1433
[2] An HMM-Based Reputation Model
ElSalamouny, Ehab
Sassone, Vladimiro
[J]. ADVANCES IN SECURITY OF INFORMATION AND COMMUNICATION NETWORKS, 2013, 381 : 111 - +
[3] HMM-Based Trust Model
Elsalamouny, Ehab
Sassone, Vladimiro
Nielsen, Mogens
[J]. FORMAL ASPECTS IN SECURITY AND TRUST, 2010, 5983 : 21 - +
[4] HMM-based concept learning for a mobile robot
Squire, Kevin M.
Levinson, Stephen E.
[J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2007, 11 (02) : 199 - 212
[5] A HMM-Based Structured Model for Human Behavior
Wang, Weihua
[J]. PROCEEDINGS OF THE 2017 5TH INTERNATIONAL CONFERENCE ON FRONTIERS OF MANUFACTURING SCIENCE AND MEASURING TECHNOLOGY (FMSMT 2017), 2017, 130 : 1599 - 1602
[6] HMM-Based Emphatic Speech Synthesis Using Unsupervised Context Labeling
Maeno, Yu
Nose, Takashi
Kobayashi, Takao
Ijima, Yusuke
Nakajima, Hideharu
Mizuno, Hideyuki
Yoshioka, Osamu
[J]. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 1860 - +
[7] Sinusoidal model parameterization for HMM-based TTS system
Shechtman, Slava
Sorin, Alex
[J]. 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 805 - 808
[8] The HMM-based model for evaluating recommender's reputation
Song, WH
Phoha, VV
Xu, X
[J]. PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON E-COMMERCE TECHNOLOGY FOR DYNAMIC E-BUSINESS, 2004, : 209 - 215
[9] HMM-based Model for Dance Motions with Pose Representation
Anbarsanti, Nurfitri
Prihatmanto, Ary S.
[J]. 2014 IEEE 4TH INTERNATIONAL CONFERENCE ON SYSTEM ENGINEERING AND TECHNOLOGY (ICSET), 2014,
[10] HMM-Based Thai Speech Synthesis Using Unsupervised Stress Context Labeling
Moungsri, Decha
Koriyama, Tomoki
Kobayashi, Takao
[J]. 2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,

← 1 2 3 4 5 →