External Links
Google Scholar
provided by
German Research Center for Artificial Intelligence
with support by
as well as by

Speech Retrieval

abbreviation(s): SDR
definition: Speech Retrieval is the process of retrieving spoken audio material (documents)in response to a search query. Search queries can be spoken or textual. Speech retrieval makes use of techniques from speech recognition, natural language understanding and information retrieval. Possible applications are the indexing of archives of broadcast material, and monitoring of telephone conversations.
See also the corresponding HLT Survey chapter: http://www.clis2.umd.edu/dlrg/speech/speechretrieval_definition.html
related project(s):
  • Multimedia Document Retrieval (MDR)
  • A Multilingual Indexing Tool for Broadcast Material Based on Speech Recognition (OLIVE)
  • Experience on Demand (Informedia)
  • Thematic Indexing of Spoken Language (THISL)
  • Rough'n'Ready
related organisation(s):
  • Carnegie Mellon University (CMU)
  • Cambridge University
  • LIMSI Spoken Language Processing Group (TLP)
  • Speech & Language Processing
  • Speech and Hearing Research Group (SPandH)
related system(s) / resource(s):
  • Podzinger
  • SAIL Technology Media Mining System
  • HP SpeechBot
related publication(s):

Proceedings of AAAI spring sympsoium Cross-Language Text and Speech Retrieval.
David Hull and Douglas Oard. 1997.

Proceedings of the ESCA ETRW workshop Accessing Information in Spoken Audio.
Tony Robinson and Steve Renals. 1999.

Speech and Language Technologies for Audio Indexing and Retrieval.
John Makhoul and Francis Kubala and Timothy Leek and Daben Liu and Long Nguyen and Richard Schwartz and Amit Srivastava.
Proceedings of the IEEE. 88 (8). 2000. 1338 -- 1353.