Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

著者

• Kawahara Tatsuya

  Kyoto Univ.

• AIKAWA Kiyoaki

  Tokyo University of Technology

• Yamashita Yoichi

  Ritsumeikan Univ. Kusatsu‐shi Jpn

• Nanjo Hiroaki

  Ryukoku University

• Nishizaki Hiromitsu

  University of Yamanashi

• Akiba Tomoyosi

  Toyohashi University of Technology

• Itoh Yoshiaki

  Iwate Prefectural University

• Yasuda Norihito

  Nippon Telegraph and Telephone Corporation

• Itou Katunobu

  Hosei University

• Kawahara Tatsuya

  Kyoto University

関連論文

• Key-Phrase Detection and Verification for Flexible Speech Understanding
• Fundamental Frequency Estimation for Noisy Speech Using Entropy-Weighted Periodic and Harmonic Features
• Omnidirectional Audio-Visual Talker Localization Based on Dynamic Fusion of Audio-Visual Features Using Validity and Reliability Criteria
• Robust Talker Direction Estimation Based on Weighted CSP Analysis and Maximum Likelihood Estimation(Speech Enhancement, Statistical Modeling for Speech Processing)
• Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data

スポンサーリンク