TY - GEN
T1 - RSHMM++ for extractive lecture speech summarization
AU - Zhang, Justin Jian
AU - Huang, Shilei
AU - Fung, Pascale
PY - 2008
Y1 - 2008
N2 - We propose an enhanced Rhetorical-State Hidden Markov Model (RSHMM++) for extracting hierarchical structural summaries from lecture speech. One of the most underutilized information in extractive summarization is rhetorical structure hidden in speech data. RSHMM++ automatically decodes this underlying information in order to provide better summaries. We show that RSHMM++ gives a 72.01% ROUGE-L F-measure, a 9.78% absolute increase in lecture speech summarization performance compared to the baseline system without using rhetorical information. We also propose Relaxed DTW for compiling reference summaries.
AB - We propose an enhanced Rhetorical-State Hidden Markov Model (RSHMM++) for extracting hierarchical structural summaries from lecture speech. One of the most underutilized information in extractive summarization is rhetorical structure hidden in speech data. RSHMM++ automatically decodes this underlying information in order to provide better summaries. We show that RSHMM++ gives a 72.01% ROUGE-L F-measure, a 9.78% absolute increase in lecture speech summarization performance compared to the baseline system without using rhetorical information. We also propose Relaxed DTW for compiling reference summaries.
KW - Rhetorical information
KW - Speech summarization
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000266764600041
UR - https://openalex.org/W2127661617
UR - https://www.scopus.com/pages/publications/67649509450
U2 - 10.1109/SLT.2008.4777865
DO - 10.1109/SLT.2008.4777865
M3 - Conference Paper published in a book
SN - 9781424434725
T3 - 2008 IEEE Workshop on Spoken Language Technology, SLT 2008 - Proceedings
SP - 161
EP - 164
BT - 2008 IEEE Workshop on Spoken Language Technology, SLT 2008 - Proceedings
PB - IEEE Computer Society
T2 - 2008 IEEE Workshop on Spoken Language Technology, SLT 2008
Y2 - 15 December 2008 through 19 December 2008
ER -