Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Linear segmentation of ASR transcripts and text by topic

: Muryshkin, Peter

Volltext urn:nbn:de:0011-n-4741773 (2.1 MByte PDF)
MD5 Fingerprint: dc4c5860866a51c41c8895718f7c7871
Erstellt am: 30.11.2017

Sankt Augustin, 2011, X, 83 S., VIII
Sankt Augustin, Hochschule Bonn-Rhein-Sieg, Master Thesis, 2011
Master Thesis, Elektronische Publikation
Fraunhofer IAIS ()

The recent explosion of available audio-visual media is the new challenge for information retrieval research. Audio speech recognition systems translate spoken content to the text domain. There is a need for searching and indexing this data which possesses no logical structure. One possible way to structure it on a high level of abstraction is by finding topic boundaries. Two unsupervised topic segmentation methods were evaluated with real-world data in the course of this work. The first one, TSF, models topic shifts as fluctuations in the similarity function of the transcript. The second one, LCSeg, approaches topic changes as places with the least overlapping lexical chains. Only LCSeg performed close to a similar real-world corpus. Other reported results could not be outperformed. Topic analysis based on the repeated word usage models renders topic changes more ambiguous than expected. This issue has more impact on the segmentation quality than the state-of-the-art ASR word error rate. It could be concluded that it is advisable to develop topic segmentation algorithms with real-world data to avoid potential biases to artificial data. Unlike evaluated approaches based on word usage analysis, methods operating with local contexts can be expected to perform better through emulation of semantic dependencies.