Speech Summarization: An Approach through Word Extraction and a Method for Evaluation

Chiori HORI; Sadaoki FURUI

Speech Summarization: An Approach through Word Extraction and a Method for Evaluation

Chiori HORI, Sadaoki FURUI

Full Text Views

0

Share
Cite this

Summary :

In this paper, we propose a new method of automatic speech summarization for each utterance, where a set of words that maximizes a summarization score is extracted from automatic speech transcriptions. The summarization score indicates the appropriateness of summarized sentences. This extraction is achieved by using a dynamic programming technique according to a target summarization ratio. This ratio is the number of characters/words in the summarized sentence divided by the number of characters/words in the original sentence. The extracted set of words is then connected to build a summarized sentence. The summarization score consists of a word significance measure, linguistic likelihood, and a confidence measure. This paper also proposes a new method of measuring summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization is calculated by comparing it with the most similar word string in the network. Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using our proposed method with 20, 40, 60, 70 and 80% summarization ratios. Experimental results reveal that the proposed method can effectively extract relatively important information by removing redundant or irrelevant information.

Publication: IEICE TRANSACTIONS on Information Vol.E87-D No.1 pp.15-25

Publication Date: 2004/01/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on the 2002 IEICE Excellent Paper Award)

Category

Cite this

Copy

Chiori HORI, Sadaoki FURUI, "Speech Summarization: An Approach through Word Extraction and a Method for Evaluation" in IEICE TRANSACTIONS on Information, vol. E87-D, no. 1, pp. 15-25, January 2004, doi: .
Abstract: In this paper, we propose a new method of automatic speech summarization for each utterance, where a set of words that maximizes a summarization score is extracted from automatic speech transcriptions. The summarization score indicates the appropriateness of summarized sentences. This extraction is achieved by using a dynamic programming technique according to a target summarization ratio. This ratio is the number of characters/words in the summarized sentence divided by the number of characters/words in the original sentence. The extracted set of words is then connected to build a summarized sentence. The summarization score consists of a word significance measure, linguistic likelihood, and a confidence measure. This paper also proposes a new method of measuring summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization is calculated by comparing it with the most similar word string in the network. Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using our proposed method with 20, 40, 60, 70 and 80% summarization ratios. Experimental results reveal that the proposed method can effectively extract relatively important information by removing redundant or irrelevant information.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e87-d_1_15/_p

Copy

@ARTICLE{e87-d_1_15,
author={Chiori HORI, Sadaoki FURUI, },
journal={IEICE TRANSACTIONS on Information},
title={Speech Summarization: An Approach through Word Extraction and a Method for Evaluation},
year={2004},
volume={E87-D},
number={1},
pages={15-25},
abstract={In this paper, we propose a new method of automatic speech summarization for each utterance, where a set of words that maximizes a summarization score is extracted from automatic speech transcriptions. The summarization score indicates the appropriateness of summarized sentences. This extraction is achieved by using a dynamic programming technique according to a target summarization ratio. This ratio is the number of characters/words in the summarized sentence divided by the number of characters/words in the original sentence. The extracted set of words is then connected to build a summarized sentence. The summarization score consists of a word significance measure, linguistic likelihood, and a confidence measure. This paper also proposes a new method of measuring summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization is calculated by comparing it with the most similar word string in the network. Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using our proposed method with 20, 40, 60, 70 and 80% summarization ratios. Experimental results reveal that the proposed method can effectively extract relatively important information by removing redundant or irrelevant information.},
keywords={},
doi={},
ISSN={},
month={January},}

Copy

TY - JOUR
TI - Speech Summarization: An Approach through Word Extraction and a Method for Evaluation
T2 - IEICE TRANSACTIONS on Information
SP - 15
EP - 25
AU - Chiori HORI
AU - Sadaoki FURUI
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2004
AB - In this paper, we propose a new method of automatic speech summarization for each utterance, where a set of words that maximizes a summarization score is extracted from automatic speech transcriptions. The summarization score indicates the appropriateness of summarized sentences. This extraction is achieved by using a dynamic programming technique according to a target summarization ratio. This ratio is the number of characters/words in the summarized sentence divided by the number of characters/words in the original sentence. The extracted set of words is then connected to build a summarized sentence. The summarization score consists of a word significance measure, linguistic likelihood, and a confidence measure. This paper also proposes a new method of measuring summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization is calculated by comparing it with the most similar word string in the network. Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using our proposed method with 20, 40, 60, 70 and 80% summarization ratios. Experimental results reveal that the proposed method can effectively extract relatively important information by removing redundant or irrelevant information.
ER -