Extractive speech summarization leveraging convolutional neural network techniques

Chun I. Tsai, Hsiao Tsung Hung, Kuan Yu Chen, Berlin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Extractive text or speech summarization endeavors to select representative sentences from a source document and assemble them into a concise summary, so as to help people to browse and assimilate the main theme of the document efficiently. The recent past has seen a surge of interest in developing deep learning- or deep neural network-based supervised methods for extractive text summarization. This paper presents a continuation of this line of research for speech summarization and its contributions are three-fold. First, we exploit an effective framework that integrates two convolutional neural networks (CNNs) and a multilayer perceptron (MLP) for summary sentence selection. Specifically, CNNs encode a given document-sentence pair into two discriminative vector embeddings separately, while MLP in turn takes the two embeddings of a document-sentence pair and their similarity measure as the input to induce a ranking score for each sentence. Second, the input of MLP is augmented by a rich set of prosodic and lexical features apart from those derived from CNNs. Third, the utility of our proposed summarization methods and several widely-used methods are extensively analyzed and compared. The empirical results seem to demonstrate the effectiveness of our summarization method in relation to several state-of-the-art methods.

Original languageEnglish
Title of host publication2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages158-164
Number of pages7
ISBN (Electronic)9781509049035
DOIs
Publication statusPublished - 2017 Feb 7
Event2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - San Diego, United States
Duration: 2016 Dec 132016 Dec 16

Publication series

Name2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

Other

Other2016 IEEE Workshop on Spoken Language Technology, SLT 2016
CountryUnited States
CitySan Diego
Period16/12/1316/12/16

Fingerprint

Multilayer neural networks
Neural networks
Speech Summarization
Neural Networks
Summarization
Summary

Keywords

  • Convolutional neural network
  • Deep learning
  • Deep neural network
  • Speech summarization

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Artificial Intelligence
  • Language and Linguistics
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Tsai, C. I., Hung, H. T., Chen, K. Y., & Chen, B. (2017). Extractive speech summarization leveraging convolutional neural network techniques. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings (pp. 158-164). [7846259] (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT.2016.7846259

Extractive speech summarization leveraging convolutional neural network techniques. / Tsai, Chun I.; Hung, Hsiao Tsung; Chen, Kuan Yu; Chen, Berlin.

2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 158-164 7846259 (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tsai, CI, Hung, HT, Chen, KY & Chen, B 2017, Extractive speech summarization leveraging convolutional neural network techniques. in 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings., 7846259, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 158-164, 2016 IEEE Workshop on Spoken Language Technology, SLT 2016, San Diego, United States, 16/12/13. https://doi.org/10.1109/SLT.2016.7846259
Tsai CI, Hung HT, Chen KY, Chen B. Extractive speech summarization leveraging convolutional neural network techniques. In 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 158-164. 7846259. (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings). https://doi.org/10.1109/SLT.2016.7846259
Tsai, Chun I. ; Hung, Hsiao Tsung ; Chen, Kuan Yu ; Chen, Berlin. / Extractive speech summarization leveraging convolutional neural network techniques. 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 158-164 (2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings).
@inproceedings{946e62b359174ee1bbc93254abc5df3c,
title = "Extractive speech summarization leveraging convolutional neural network techniques",
abstract = "Extractive text or speech summarization endeavors to select representative sentences from a source document and assemble them into a concise summary, so as to help people to browse and assimilate the main theme of the document efficiently. The recent past has seen a surge of interest in developing deep learning- or deep neural network-based supervised methods for extractive text summarization. This paper presents a continuation of this line of research for speech summarization and its contributions are three-fold. First, we exploit an effective framework that integrates two convolutional neural networks (CNNs) and a multilayer perceptron (MLP) for summary sentence selection. Specifically, CNNs encode a given document-sentence pair into two discriminative vector embeddings separately, while MLP in turn takes the two embeddings of a document-sentence pair and their similarity measure as the input to induce a ranking score for each sentence. Second, the input of MLP is augmented by a rich set of prosodic and lexical features apart from those derived from CNNs. Third, the utility of our proposed summarization methods and several widely-used methods are extensively analyzed and compared. The empirical results seem to demonstrate the effectiveness of our summarization method in relation to several state-of-the-art methods.",
keywords = "Convolutional neural network, Deep learning, Deep neural network, Speech summarization",
author = "Tsai, {Chun I.} and Hung, {Hsiao Tsung} and Chen, {Kuan Yu} and Berlin Chen",
year = "2017",
month = "2",
day = "7",
doi = "10.1109/SLT.2016.7846259",
language = "English",
series = "2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "158--164",
booktitle = "2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings",

}

TY - GEN

T1 - Extractive speech summarization leveraging convolutional neural network techniques

AU - Tsai, Chun I.

AU - Hung, Hsiao Tsung

AU - Chen, Kuan Yu

AU - Chen, Berlin

PY - 2017/2/7

Y1 - 2017/2/7

N2 - Extractive text or speech summarization endeavors to select representative sentences from a source document and assemble them into a concise summary, so as to help people to browse and assimilate the main theme of the document efficiently. The recent past has seen a surge of interest in developing deep learning- or deep neural network-based supervised methods for extractive text summarization. This paper presents a continuation of this line of research for speech summarization and its contributions are three-fold. First, we exploit an effective framework that integrates two convolutional neural networks (CNNs) and a multilayer perceptron (MLP) for summary sentence selection. Specifically, CNNs encode a given document-sentence pair into two discriminative vector embeddings separately, while MLP in turn takes the two embeddings of a document-sentence pair and their similarity measure as the input to induce a ranking score for each sentence. Second, the input of MLP is augmented by a rich set of prosodic and lexical features apart from those derived from CNNs. Third, the utility of our proposed summarization methods and several widely-used methods are extensively analyzed and compared. The empirical results seem to demonstrate the effectiveness of our summarization method in relation to several state-of-the-art methods.

AB - Extractive text or speech summarization endeavors to select representative sentences from a source document and assemble them into a concise summary, so as to help people to browse and assimilate the main theme of the document efficiently. The recent past has seen a surge of interest in developing deep learning- or deep neural network-based supervised methods for extractive text summarization. This paper presents a continuation of this line of research for speech summarization and its contributions are three-fold. First, we exploit an effective framework that integrates two convolutional neural networks (CNNs) and a multilayer perceptron (MLP) for summary sentence selection. Specifically, CNNs encode a given document-sentence pair into two discriminative vector embeddings separately, while MLP in turn takes the two embeddings of a document-sentence pair and their similarity measure as the input to induce a ranking score for each sentence. Second, the input of MLP is augmented by a rich set of prosodic and lexical features apart from those derived from CNNs. Third, the utility of our proposed summarization methods and several widely-used methods are extensively analyzed and compared. The empirical results seem to demonstrate the effectiveness of our summarization method in relation to several state-of-the-art methods.

KW - Convolutional neural network

KW - Deep learning

KW - Deep neural network

KW - Speech summarization

UR - http://www.scopus.com/inward/record.url?scp=85016007335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016007335&partnerID=8YFLogxK

U2 - 10.1109/SLT.2016.7846259

DO - 10.1109/SLT.2016.7846259

M3 - Conference contribution

AN - SCOPUS:85016007335

T3 - 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

SP - 158

EP - 164

BT - 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -