Relevant Documents Selection for Blind Relevance Feedback in Speech Information Retrieval

详细信息    查看全文

• 关键词：Query expansion ; Blind relevance feedback ; Spoken document retrieval ; Score normalization
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9924
• 期：1
• 页码：418-425
• 全文大小：148 KB
• 参考文献：1.Ircing, P., Pecina, P., Oard, D.W., Wang, J., White, R.W., Hoidekr, J.: Information retrieval test collection for searching spontaneous Czech speech. In: Matoušek, V., Mautner, P. (eds.) TSD 2007. LNCS (LNAI), vol. 4629, pp. 439–446. Springer, Heidelberg (2007)CrossRef
  2.Sivakumaran, P., Fortuna, J., Ariyaeeinia, M.A.: Score normalisation applied to open-set, text-independent speaker identification. In: Proceedings of Eurospeech, Geneva, pp. 2669–2672 (2003)
  3.Zajíc, Z., Machlica, L., Padrta, A., Vaněk, J., Radová, V.: An expert system in speaker verification task. In: Proceedings of Interspeech, vol. 9, pp. 355–358. International Speech Communication Association, Brisbane (2008)
  4.Skorkovská, L.: First experiments with relevant documents selection for blind relevance feedback in spoken document retrieval. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS, vol. 8773, pp. 235–242. Springer, Heidelberg (2014)
  5.Skorkovská, L.: Score normalization methods for relevant documents selection for blind relevance feedback in speech information retrieval. In: Král, P., Matoušek, V. (eds.) TSD 2015. LNCS, vol. 9302, pp. 316–324. Springer, Heidelberg (2015)CrossRef
  6.Ircing, P., Psutka, J.V., Vavruška, J.: What can and cannot be found in Czech spontaneous speech using document-oriented IR methods — UWB at CLEF 2007 CL-SR track. In: Peters, C., Jijkoun, V., Mandl, T., Müller, H., Oard, D.W., Peñas, A., Petras, V., Santos, D. (eds.) CLEF 2007. LNCS, vol. 5152, pp. 712–718. Springer, Heidelberg (2008)CrossRef
  7.Ponte, J.M., Croft, W.B.: A language modeling approach to information retrieval. In: Proceedings of SIGIR 1998, pp. 275–281. ACM, New York (1998)
  8.Kanis, J., Skorkovská, L.: Comparison of different lemmatization approaches through the means of information retrieval performance. In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds.) TSD 2010. LNCS, vol. 6231, pp. 93–100. Springer, Heidelberg (2010)CrossRef
  9.Salton, G., Wong, A., Yang, C.S.: A vector space model for automatic indexing. Commun. ACM 18(11), 613–620 (1975)CrossRef MATH
  10.Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted Gaussian mixture models. Digit. Sig. Process. 10, 19–41 (2000)CrossRef
  11.Auckenthaler, R., Carey, M., Lloyd-Thomas, H.: Score normalization for text-independent speaker verification systems. Digit. Signal Process. 10(1–3), 42–54 (2000)CrossRef
  12.Liu, B., Oard, D.W.: One-sided measures for evaluating ranked retrieval effectiveness with spontaneous conversational speech. In: Proceedings of ACM SIGIR 2006, SIGIR 2006, pp. 673–674. ACM, New York (2006)
  
• 作者单位：Lucie Skorkovská (17)
  
  17. New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Univerzitní 8, 306 14, Plzeň, Czech Republic
  
• 丛书名：Text, Speech, and Dialogue
• ISBN：978-3-319-45510-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9924

文摘

The experiments presented in this paper were aimed at the selection of documents to be used in the blind or pseudo relevance feedback in spoken document retrieval. The previous experiments with the automatic selection of the relevant documents for the blind relevance feedback method have shown the possibilities of the dynamical selection of the relevant documents for each query depending on the content of the retrieved documents instead of just blindly defining the number of the relevant documents to be used in advance. The score normalization techniques commonly used in the speaker identification task are used for the dynamical selection of the relevant documents. In the previous experiments, the language modeling information retrieval method was used. In the experiments presented in this paper, we have derived the score normalization technique also for the vector space information retrieval method. The results of our experiments show, that these normalization techniques are not method-dependent and can be successfully used in several information retrieval system settings.