Abstract
Traditionally, the query words in spoken document classification are generated by manual. Here, based on CHI, TFIDF and maximum poster probability (MPP) features, key information extraction is combined with spoken document classification system, where different class has different topic. From the extraction, the weights of the same key word in each topic may be distinct. These weights which reveal the relationship between the word and topic can be taken part in spoken document classification system. Additionally, in the classification system, document length information is adopted when no query is found. The whole classification system is based on lattice, which has more information than 1-best result in speech recognition system. Among CHI, TFIDF and MPP, the system performance of MPP is a little worse than the others. CHI is a little better than TFIDF when the key words number is increasing. Experiments show that when the system is combined weight and document length information, the best performance can achieve 0.769 MAP.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chang, Y.-L., Chen, J.-T.: Latent Dirichlet Learning for Document Summarization. In: ICASSP 2009, pp. 1689–1692. IEEE Press, TaiWan (2009)
Malian, J.T., Throop, D.R.: Basic Concepts and Distinctions for an Aerospace Ontology of Functions, Entities and Problems. In: Aerospace Conf., pp. 1–18. IEEE Press, Big Sky (2007)
Chen, B., Wang, H.-M., Lee, L.-S.: Retrieval of Broadcast News Speech in Mandarin Chinese Collected in Taiwan Using Syllable-level Statistical Characteristics. In: ICASSP 2000, pp. 1771–1774. IEEE Press, Istanbul (2000)
Meng, C.-H., Lee, H.-Y., Lee, L.-S.: Improved Lattice-based Spoken Document Retrieval by Directly Learning from the Evaluation Measures. In: ICASSP 2009, pp. 4893–4896. IEEE Press, Taiwan (2009)
Mertens, T., Schneider, D.: Efficient Sub-word Lattice Retrieval for German Spoken Term Detection. In: ICASSP2009, pp. 4885–4888. IEEE Press, Taipei (2009)
Zhang, L., Gao, Y., Xang, X., Lu, D.: A New Syllable-lattice Based Approach for Mandarin Spoken Document Retrieval. In: Wireless Communications & Signal Processing, pp. 1–4. IEEE Press, ShangHai (2009)
Yang, Y.-M., Pedersen, J.O.: A Comparative Study on Feature Selection in Text Categorization. In: Proc. ICML-14, pp. 12–420 (1997)
Hazen, T.J., Richardson, F., Margolis, A.: Anna Margolis.: Topic Identification from Audio Recordings using Word and Phone Recognition Lattices. In: ASRU 2007, pp.659–664 (2007)
Chen, B., Wang, H.M., Lee, L.S.: A Discriminative HMM/N-gram-based Retrieval Approach for Mandarin Spoken Documents. ACM Trans. Asian Lang. Inform. Process. 3(2), 128–145 (2004)
Blanco, R., Barreiro, Á.: Probabilistic Document Length Priors for Language Models. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol. 4956, pp. 394–405. Springer, Heidelberg (2008)
Zhai, C.-X., Lafferty, J.: A Study of Smoothing Methods for Language Models Applied to Information Retrieval. ACM Trans. Information Systems 22(2), 179–214 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, L., Zhang, Z., Xiang, Xz. (2011). Combination of Key Information Extracting with Spoken Document Classification Based on Lattice. In: Yu, Y., Yu, Z., Zhao, J. (eds) Computer Science for Environmental Engineering and EcoInformatics. CSEEE 2011. Communications in Computer and Information Science, vol 159. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22691-5_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-22691-5_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22690-8
Online ISBN: 978-3-642-22691-5
eBook Packages: Computer ScienceComputer Science (R0)