The spoken web search task at MediaEval 2012

Author

Metze, Florian ; Anguera, Xavier ; Barnard, Etienne ; Davel, Marelie ; Gravier, Guillaume

Author_Institution

Carnegie Mellon Univ., Pittsburgh, PA, USA

fYear

2013

Firstpage

8121

Lastpage

8125

Abstract

In this paper, we describe the “Spoken Web Search” Task, which was held as part of the 2012 MediaEval benchmark evaluation campaign. The purpose of this task was to perform audio search with audio input in four languages, with very few resources being available. Continuing in the spirit of the 2011 SpokenWeb Search Task, which used speech from four Indian languages, the 2012 data was taken from the LWAZI corpus, to provide even more diversity and allow for a task that will allow both zero resource “pattern matching” approaches and “speech recognition” based approaches to participate. In this paper, we summarize the results from several independent systems, developed by nine teams, analyze their performance, and provide directions for future research.

Keywords

Internet; audio signal processing; natural language processing; pattern matching; speech recognition; 2012 MediaEval benchmark evaluation campaign; Indian languages; LWAZI corpus; audio search; independent systems; speech recognition based approach; spoken Web search task; zero resource pattern matching approach; Acoustics; Conferences; Feature extraction; Hidden Markov models; Speech; Speech recognition; Web search; evaluation; low-resource speech recognition; pattern matching; spoken term detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on

Conference_Location

Vancouver, BC

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2013.6639247

Filename

6639247