https://scholars.lib.ntu.edu.tw/handle/123456789/377562
標題: | Interactive spoken content retrieval by extended query model and continuous state space Markov Decision Process | 作者: | Wen, T.-H. Su, P.-H. HUNG-YI LEE LIN-SHAN LEE |
關鍵字: | Fitted Value Iteration; Interactive Retrieval; Language Model Retrieval; Markov Decision Process; MDP | 公開日期: | 2013 | 起(迄)頁: | 8510-8514 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing | 摘要: | Interactive retrieval is important for spoken content because the retrieved spoken items are not only difficult to be shown on the screen but also scanned and selected by the user, in addition to the speech recognition uncertainty. The user cannot playback and go through all the retrieved items to find out what he is looking for. Markov Decision Process (MDP) was used in a previous work to help the system take different actions to interact with the user based on an estimated retrieval performance, but the MDP state was represented by the less precise quantized retrieval performance metric. In this paper, we consider the retrieval performance metric as a continuous state variable in MDP and optimize the MDP by fitted value iteration (FVI).We also use query expansion with the language modeling retrieval framework to produce the next set of retrieval results. Improved performance was found in the preliminary experiments. © 2013 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84890497192&doi=10.1109%2fICASSP.2013.6639326&partnerID=40&md5=a31f2e432d644344ec6df1cb1eefdbc5 http://scholars.lib.ntu.edu.tw/handle/123456789/377562 |
DOI: | 10.1109/ICASSP.2013.6639326 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。