Rapid development of a Latvian speech-to-text system

Author

Oparin, Ilya ; Lamel, Lori ; Gauvain, Jean-Luc

Author_Institution

LNE (Nat. Metrol. & Testing Lab.), Trappes, France

fYear

2013

Firstpage

7309

Lastpage

7313

Abstract

This paper describes the development of a Latvian speech-to-text (STT) system at LIMSI within the Quaero project. One of the aims of the speech processing activities in the Quaero project is to cover all official European languages. However, for some of the languages only very limited, if any, training resources are available via corpora agencies such as LDC and ELRA. The aim of this study was to show the way, taking Latvian as example, an STT system can be rapidly developed without any transcribed training data. Following the scheme proposed in this paper, the Latvian STT system was developed in about a month and obtained a word error rate of 20% on broadcast news and conversation data in the Quaero 2012 evaluation campaign.

Keywords

error statistics; speech synthesis; ELRA; LDC; LIMSI; Latvian STT system; Latvian speech-to-text system; Quaero 2012 evaluation campaign; broadcast news; conversation data; corpora agencies; official European languages; speech processing activities; training resources; word error rate; Acoustics; Artificial neural networks; Data models; Hidden Markov models; Speech; Speech recognition; Training; Latvian; Speech recognition; under-resourced language;

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.2013.6639082

Filename

6639082