音声ドキュメント検索評価のためのテストコレクションの試作  [in Japanese] A Prototype of a Test Collection for evaluation of Spoken Document Retrieval System  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

情報処理学会音声言語情報処理研究会の音声ドキュメント処理ワーキンググループの活動の一環として行っている、音声ドキュメント検索評価用テストコレクションについて報告する。試作したテストコレクションは、対象を日本語話し言葉コーパス(CSJ)の講演音声データならびに書き起こしデータとし、テキストクエリとそれに対する正解データ、ならびに音声認識結果から構成される。答が1分前後の音声区間となり、5区間程度の正解が得られるようなクエリを目標に作成して、正解判定をしたところ100件程度作成したクエリのうち、33件のクエリが条件を満たしていた。The Spoken Document Processing Working Group, Which is organized in special interest group of spoken language processing, information processing society of Japan, are developing a test collection for evaluation of spoken document retrieval system. A prototype of the test collection consists of a set of textual queries, relevant segment lists, and the transcription by the automatic speech recognition system to retrieve from the Corpus of Spontaneous Japanese (CSJ). As a result to design qureies according to the criteria that a query should have more than five relevant segments that consist from about one minute speech segment, thirty three queries were obtained among about 100 queries.

The Spoken Document Processing Working Group, which is organized in special interest group of spoken language processing, information processing society of Japan, are developing a test collection for evaluation of spoken document retrieval system. A prototype of the test collection consists of a set of textual queries, relevant segment lists, and the transcription by the automatic speech recognition system to retrieve from the Corpus of Spontaneous Japanese (CSJ). As a result to design queries according to the criteria that a query should have more than five relevant segments that consist from about one minute speech segment, thirty three queries were obtained among about 100 queries.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 2006(136(2006-SLP-064)), 137-142, 2006-12-21

    Information Processing Society of Japan (IPSJ)

References:  13

Cited by:  6

Codes

  • NII Article ID (NAID)
    110006248332
  • NII NACSIS-CAT ID (NCID)
    AN10442647
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09196072
  • NDL Article ID
    8600750
  • NDL Source Classification
    ZM13(科学技術--科学技術一般--データ処理・計算機)
  • NDL Call No.
    Z14-1121
  • Data Source
    CJP  CJPref  NDL  NII-ELS  IPSJ 
Page Top