The development of ASR for Slavic languages in the MALACH project

Author

Psutka, Josef ; Haj, Jan ; Byrne, William

Author_Institution

Dept. Cybern. & Center for Comput. Linguistics, Univ. of West Bohemia, Czech Republic

Volume

3

fYear

2004

fDate

17-21 May 2004

Abstract

The development of acoustic training material for Slavic languages within the MALACH project is described. Initial experience with the variety of speakers and the difficulties encountered in transcribing Czech, Slovak, and Russian language oral history are described along with automatic speech recognition results intended to investigate the effectiveness of different transcription conventions that address language specific phenomena within the task domain.

Keywords

history; linguistics; natural languages; speech processing; speech recognition; ASR; Czech language; MALACH project; Russian language; Slavic languages; Slovak language; acoustic training material; automatic speech recognition; language specific phenomena; language transcription; multilingual access to large spoken archives; spontaneous oral history; Acoustic noise; Automatic speech recognition; Background noise; Computational linguistics; Cybernetics; History; Mouth; Natural languages; Testing; White spaces;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1326653

Filename

1326653