Spoken term detection for Turkish Broadcast News

Author

Parlak, Siddika ; Saraçlar, Murat

Author_Institution

Dept. of Electr. & Electron. Eng., Bogazici Univ., Istanbul

fYear

2008

fDate

March 31 2008-April 4 2008

Firstpage

5244

Lastpage

5247

Abstract

In this paper, we present a baseline spoken term detection (STD) system for Turkish broadcast news. The agglutinative structure of Turkish causes a high out-of-vocabulary (OOV) rate and increases word error rate (WER) in automatic speech recognition. Several approaches are attempted to reduce this negative effect on the STD system. Sub-word units are used to handle the OOV queries and lattice-based indexing is used to obtain different operating points and handle high WER cases. A recently proposed method for setting term specific thresholds is also evaluated and extended to allow us to choose an operating point suitable for our needs. Best results are obtained by using a cascade of word and sub-word lattice indices with term-thresholding.

Keywords

indexing; information retrieval; speech recognition; text analysis; word processing; Turkish broadcast news; automatic speech recognition; lattice-based indexing; out-of-vocabulary queries; spoken term detection; sub-word lattice indices; term-thresholding; word error rate; Automatic speech recognition; Broadcasting; Design methodology; Error analysis; Handicapped aids; Indexing; Information retrieval; Lattices; Speech processing; Speech recognition; audio indexing; information retrieval; speech recognition; spoken term detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on

Conference_Location

Las Vegas, NV

ISSN

1520-6149

Print_ISBN

978-1-4244-1483-3

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2008.4518842

Filename

4518842