论文信息 - Overview of the NTCIR-10 SpokenDoc-2 Task

Overview of the NTCIR-10 SpokenDoc-2 Task

This paper describes an overview of the IR for Spoken Documents Task in NTCIR-10 Workshop. In this task, the spoken term detection (STD) subtask and ad-hoc spoken content retrieval subtask (SCR) are conducted. Both of the tasks target to search terms, passages and documents included in academic oral presentations. This paper explains the data used in the tasks, how to make transcriptions by speech recognition and the details of each tasks.

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

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

[3] Tatsuya Kawahara,et al. Designing an Evaluation Framework for Spoken Term Detection and Spoken Document Retrieval at the NTCIR-9 SpokenDoc Task , 2012, LREC.

[4] Hitoshi Isahara,et al. Spontaneous Speech Corpus of Japanese , 2000, LREC.

[5] Tatsuya Kawahara,et al. Recent Development of Open-Source Speech Recognition Engine Julius , 2009 .