@article{oai:ipsj.ixsq.nii.ac.jp:00009269, author = {Tomoyosi, Akiba and Kiyoaki, Aikawa and Yoshiaki, Itoh and Tatsuya, Kawahara and Hiroaki, Nanjo and Hiromitsu, Nishizaki and Norihito, Yasuda and Yoichi, Yamashita and Katunobu, Itou and Tomoyosi, Akiba and Kiyoaki, Aikawa and Yoshiaki, Itoh and Tatsuya, Kawahara and Hiroaki, Nanjo and Hiromitsu, Nishizaki and Norihito, Yasuda and Yoichi, Yamashita and Katunobu, Itou}, issue = {2}, journal = {情報処理学会論文誌}, month = {Feb}, note = {The lecture is one of the most valuable genres of audiovisual data. Though spoken document processing is a promising technology for utilizing the lecture in various ways, it is difficult to evaluate because the evaluation require a subjective judgment and/or the verification of large quantities of evaluation data. In this paper, a test collection for the evaluation of spoken lecture retrieval is reported. The test collection consists of the target spoken documents of about 2,700 lectures (604 hours) taken from the Corpus of Spontaneous Japanese (CSJ), 39 retrieval queries, the relevant passages in the target documents for each query, and the automatic transcription of the target speech data. This paper also reports the retrieval performance targeting the constructed test collection by applying a standard spoken document retrieval (SDR) method, which serves as a baseline for the forthcoming SDR studies using the test collection., The lecture is one of the most valuable genres of audiovisual data. Though spoken document processing is a promising technology for utilizing the lecture in various ways, it is difficult to evaluate because the evaluation require a subjective judgment and/or the verification of large quantities of evaluation data. In this paper, a test collection for the evaluation of spoken lecture retrieval is reported. The test collection consists of the target spoken documents of about 2,700 lectures (604 hours) taken from the Corpus of Spontaneous Japanese (CSJ), 39 retrieval queries, the relevant passages in the target documents for each query, and the automatic transcription of the target speech data. This paper also reports the retrieval performance targeting the constructed test collection by applying a standard spoken document retrieval (SDR) method, which serves as a baseline for the forthcoming SDR studies using the test collection.}, pages = {501--513}, title = {Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data}, volume = {50}, year = {2009} }