Language model expansion using webdata for spoken document retrieval

Ryo Masumura, Seongjun Hahm, Akinori Ito

Research output: Contribution to journalConference articlepeer-review

9 Citations (Scopus)

Abstract

In recent years, there has been increasing demand for ad hoc retrieval of spoken documents. We can use existing text retrieval methods by transcribing spoken documents into text data using a Large Vocabulary Continuous Speech Recognizer (LVCSR). However, retrieval performance is severely deteriorated by recognition errors and out-of-vocabulary (OOV) words. To solve these problems, we previously proposed an expansion method that compensates the transcription by using text data downloaded from the Web. In this paper, we introduce two improvements to the existing document expansion frame- work. First, we use a large-scale sample database of webdata as the source of relevant documents, thus avoiding the bias introduced by choosing keywords in the existing methods. Next, we use a document retrieval method based on a statistical language model (SLM), which is a popular framework in information retrieval, and also propose a new smoothing method considering recognition errors and missing keywords. Retrieval experiments show that the proposed methods yield a good results.

Original languageEnglish
Pages (from-to)2133-2136
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2011 Dec 1
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: 2011 Aug 272011 Aug 31

Keywords

  • Spoken document retrieval
  • Statistical language models
  • World Wide Web

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Language model expansion using webdata for spoken document retrieval'. Together they form a unique fingerprint.

Cite this