Improved speech summarization with multiple-hypothesis representations and Kullback-Leibler divergence measures

Shih Hsiang Lin; Berlin Chen

doi:10.21437/interspeech.2009-537

Improved speech summarization with multiple-hypothesis representations and Kullback-Leibler divergence measures

Shih Hsiang Lin^*, Berlin Chen

^*Corresponding author for this work

Department of Computer Science and Information Engineering

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

23 Citations (Scopus)

Abstract

Imperfect speech recognition often leads to degraded performance when leveraging existing text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a new summarization method stemming from the Kullback-Leibler (KL) divergence measure and exploring both the sentence and document relevance information is proposed to work with such robust representations. Experiments on broadcast news speech summarization seem to demonstrate the utility of the presented approaches.

Original language	English
Pages (from-to)	1847-1850
Number of pages	4
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
DOIs	https://doi.org/10.21437/interspeech.2009-537
Publication status	Published - 2009
Event	10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom Duration: 2009 Sept 6 → 2009 Sept 10

Keywords

KL divergence
Multiple recognition hypotheses
Relevance information
Speech summarization

ASJC Scopus subject areas

Human-Computer Interaction
Signal Processing
Software
Sensory Systems

Access to Document

10.21437/interspeech.2009-537

Cite this

@article{a8eed67eea464a1693f5ecf51c116987,

title = "Improved speech summarization with multiple-hypothesis representations and Kullback-Leibler divergence measures",

abstract = "Imperfect speech recognition often leads to degraded performance when leveraging existing text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a new summarization method stemming from the Kullback-Leibler (KL) divergence measure and exploring both the sentence and document relevance information is proposed to work with such robust representations. Experiments on broadcast news speech summarization seem to demonstrate the utility of the presented approaches.",

keywords = "KL divergence, Multiple recognition hypotheses, Relevance information, Speech summarization",

author = "Lin, {Shih Hsiang} and Berlin Chen",

year = "2009",

doi = "10.21437/interspeech.2009-537",

language = "English",

pages = "1847--1850",

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 - Improved speech summarization with multiple-hypothesis representations and Kullback-Leibler divergence measures

AU - Lin, Shih Hsiang

AU - Chen, Berlin

PY - 2009

Y1 - 2009

N2 - Imperfect speech recognition often leads to degraded performance when leveraging existing text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a new summarization method stemming from the Kullback-Leibler (KL) divergence measure and exploring both the sentence and document relevance information is proposed to work with such robust representations. Experiments on broadcast news speech summarization seem to demonstrate the utility of the presented approaches.

AB - Imperfect speech recognition often leads to degraded performance when leveraging existing text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a new summarization method stemming from the Kullback-Leibler (KL) divergence measure and exploring both the sentence and document relevance information is proposed to work with such robust representations. Experiments on broadcast news speech summarization seem to demonstrate the utility of the presented approaches.

KW - KL divergence

KW - Multiple recognition hypotheses

KW - Relevance information

KW - Speech summarization

UR - http://www.scopus.com/inward/record.url?scp=70450205875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450205875&partnerID=8YFLogxK

U2 - 10.21437/interspeech.2009-537

DO - 10.21437/interspeech.2009-537

M3 - Conference article

AN - SCOPUS:70450205875

SN - 2308-457X

SP - 1847

EP - 1850

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 -

Improved speech summarization with multiple-hypothesis representations and Kullback-Leibler divergence measures

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this