Abstract
Speech summarization, distilling important information and removing redundant and incorrect information from spoken documents, has become an active area of intensive research in the recent past. In this paper, we consider hybrids of supervised and unsupervised models for extractive speech summarization. Moreover, we investigate the use of the unsupervised summarizer to improve the performance of the supervised summarizer when manual labels are not available for training the latter. A novel training data selection and relabeling approach designed to leverage the inter-document or/and the inter-sentence similarity information is explored as well. Encouraging results were initially demonstrated.
Original language | English |
---|---|
Pages (from-to) | 1507-1510 |
Number of pages | 4 |
Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
Publication status | Published - 2009 Nov 26 |
Event | 10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom Duration: 2009 Sep 6 → 2009 Sep 10 |
Fingerprint
Keywords
- Hybrid summarizer
- Speech summarization
- Unsupervised training
ASJC Scopus subject areas
- Human-Computer Interaction
- Signal Processing
- Software
- Sensory Systems
Cite this
Hybrids of supervised and unsupervised models for extractive speech summarization. / Lin, Shih Hsiang; Lo, Yueng Tien; Yeh, Yao Ming; Chen, Berlin.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 26.11.2009, p. 1507-1510.Research output: Contribution to journal › Conference article
}
TY - JOUR
T1 - Hybrids of supervised and unsupervised models for extractive speech summarization
AU - Lin, Shih Hsiang
AU - Lo, Yueng Tien
AU - Yeh, Yao Ming
AU - Chen, Berlin
PY - 2009/11/26
Y1 - 2009/11/26
N2 - Speech summarization, distilling important information and removing redundant and incorrect information from spoken documents, has become an active area of intensive research in the recent past. In this paper, we consider hybrids of supervised and unsupervised models for extractive speech summarization. Moreover, we investigate the use of the unsupervised summarizer to improve the performance of the supervised summarizer when manual labels are not available for training the latter. A novel training data selection and relabeling approach designed to leverage the inter-document or/and the inter-sentence similarity information is explored as well. Encouraging results were initially demonstrated.
AB - Speech summarization, distilling important information and removing redundant and incorrect information from spoken documents, has become an active area of intensive research in the recent past. In this paper, we consider hybrids of supervised and unsupervised models for extractive speech summarization. Moreover, we investigate the use of the unsupervised summarizer to improve the performance of the supervised summarizer when manual labels are not available for training the latter. A novel training data selection and relabeling approach designed to leverage the inter-document or/and the inter-sentence similarity information is explored as well. Encouraging results were initially demonstrated.
KW - Hybrid summarizer
KW - Speech summarization
KW - Unsupervised training
UR - http://www.scopus.com/inward/record.url?scp=70450172177&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70450172177&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:70450172177
SP - 1507
EP - 1510
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
SN - 2308-457X
ER -