caa a22 4500 605468397 CHVBK 20210128100316.0 cr unu---uuuuu 210128e20150101xx s 000 0 eng 10.1007/s00500-014-1383-9 doi (NATIONALLICENCE)springer-10.1007/s00500-014-1383-9 Topic segmentation on spoken documents using self-validated acoustic cuts [Elektronische Daten] [Hongjie Chen, Lei Xie, Wei Feng, Lilei Zheng, Yanning Zhang] Topic segmentation serves as a necessary prerequisite for multimedia content analysis and management. The normalized cuts (NCuts) approach has shown superior performance in topic segmentation of spoken document. However, in this method, the number of topics in a document has to be known prior to segmentation. This is impractical for real-world applications with exponential growth of multimedia data. On the other hand, previous lexical-based spoken document segmentation approaches, including NCuts, work on text transcripts generated by a large vocabulary continuous speech recognizer (LVCSR). As we know, training such a recognizer requires a large amount of transcribed speech data and language-specific knowledges. Moreover, inevitable speech recognition errors and the out-of-vocabulary (OOV) problem apparently affect the segmentation performance. This paper addresses these problems by a self-validated acoustic normalized cuts approach, namely SACuts. First, as compared with NCuts, our approach can determine the topic number in a spoken document automatically without extra computation load. Second, as compared with lexical approaches that rely on a high-resource speech recognizer, our approach can achieve comparable and even better segmentation performance using only acoustic-level information. Evaluation on a broadcast news topic segmentation task shows the superiority of the proposed approach. Springer-Verlag Berlin Heidelberg, 2014 Topic segmentation nationallicence Story segmentation nationallicence Topic boundary detection nationallicence Spoken document retrieval nationallicence Normalized cuts nationallicence Chen Hongjie School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut Xie Lei School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut Feng Wei School of Computer Science, Tianjin University, Tianjin, People's Republic of China aut Zheng Lilei School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut Zhang Yanning School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut Soft Computing Springer Berlin Heidelberg 19/1(2015-01-01), 47-59 1432-7643 19:1<47 2015 19 500 https://doi.org/10.1007/s00500-014-1383-9 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00500-014-1383-9 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Chen Hongjie School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Xie Lei School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Feng Wei School of Computer Science, Tianjin University, Tianjin, People's Republic of China aut NATIONALLICENCE 700 1- Zheng Lilei School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Zhang Yanning School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 773 0- Soft Computing Springer Berlin Heidelberg 19/1(2015-01-01), 47-59 1432-7643 19:1<47 2015 19 500