This paper proposes an improved method of summarizing speech in which a confidence measure of a word hypothesis is incorporated in the summarization score and also proposes a new method for evaluating the summarized sentences. The automatically summarized sentences were evaluated based on the precision of extracted keywords and each word string with a certain length in the manual summarizations by human subjects. Japanese broadcast-news speech transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system was summarized using our proposed method. Experimental results show that a confidence score giving a penalty for acoustically as well as linguistically unreliable hypotheses can reduce the meaning alteration of summarizations caused by recognition errors especially when the speech recognition rate is relatively low.
Cite as: Hori, C., Furui, S. (2000) Improvements in automatic speech summarization and evaluation methods. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 326-329, doi: 10.21437/ICSLP.2000-816
@inproceedings{hori00_icslp,
author={Chiori Hori and Sadaoki Furui},
title={{Improvements in automatic speech summarization and evaluation methods}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 326-329},
doi={10.21437/ICSLP.2000-816}
}