论文信息 - Spoken Document Retrieval Experiments for SpokenDoc at Ryukoku University (RYSDT)

Spoken Document Retrieval Experiments for SpokenDoc at Ryukoku University (RYSDT)

In this paper, we describe spoken document retrieval systems in Ryukoku University, which were participated in NTCIR-9 IR for Spoken Documents (“SpokenDoc”) task. In NTCIR-9 “SpokenDoc” task, there are two subtasks: “Spoken term detection (STD) subtask” and “Spoken document retrieval (SDR) subtask”. We participated in the both subtasks as team RYSDT. In this paper, first, our STD systems are described, and then, our SDR systems are described.

Hiroaki Nanjo | Takehiko Yoshimi | Tomohiro Nishio

[1] Chris Buckley,et al. Pivoted Document Length Normalization , 1996, SIGIR Forum.

[2] Makoto Iwayama,et al. Information Access Based on Associative Calculation , 2000, SOFSEM.

[3] Hiroaki Nanjo,et al. Spoken document retrieval for oral presentations integrating global document similarities into local document similarities , 2010, INTERSPEECH.

[4] Hiroaki Nanjo,et al. Image Processing Filters for Line Detection-Based Spoken Term Detection , 2011, INTERSPEECH.

[5] Tatsuya Kawahara,et al. Overview of the IR for Spoken Documents Task in NTCIR-9 Workshop , 2011, NTCIR.

[6] Tatsuya Kawahara,et al. Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data , 2009, J. Inf. Process..

[7] Tomoyosi Akiba,et al. Metric subspace indexing for fast spoken term detection , 2010, INTERSPEECH.