Automatic indexing of key sentences for lecture archives using statistics of presumed discourse markers

• Published in: 2004 IEEE International Conference on Acoustics, Speech and Signal Processing Vol. 1; pp. I - 449
• Main Authors: Nanjo, H., Kitade, T., Kawahara, T.
• Format: Conference Proceeding
• Language: English; Japanese
• Published: Piscataway, N.J IEEE 28.09.2004
• Subjects: Acoustic testing; Applied sciences; Automatic speech recognition; Data mining; Exact sciences and technology; Informatics; Information, signal and communications theory; Machine assisted indexing; Natural languages; Robustness; Signal and communications theory; Signal representation. Spectral analysis; Signal, noise; Speech recognition; Statistics; Telecommunications and information theory; Vocabulary; Performance evaluation; Archive; Keyword; Segmentation; Unsupervised classification; Signal classification; Accuracy; Prosody; Automatic indexing; Signal processing; Feature extraction; Discourse analysis; Automatic recognition
• ISBN: 9780780384842; 0780384849
• ISSN: 1520-6149
• DOI: 10.1109/ICASSP.2004.1326019

Automatic extraction of key sentences from lecture audio archives is addressed. The method makes use of the characteristic expressions used in initial utterances of sections, which are defined as discourse markers and derived in a totally unsupervised manner based on word statistics. The statistics of the presumed discourse markers are then used to define the importance of the sentences. It is also combined with the conventional tf-idf measure of content words. Experimental results using a large corpus of lectures confirm the effectiveness of the method based on the discourse markers and its combination with the keyword-based method. It is also shown that the method is robust against ASR errors and sentence segmentation accuracy is more vital. Thus, we also enhance segmentation by incorporating prosodic information.