Third Workshop on Spoken Language Technologies for Under-resourced Languages

Cape Town, South Africa
May 7-9, 2012

Transcription of Russian Conversational Speech

Lori Lamel (1,2), Sandrine Courcinous (2), Jean-Luc Gauvain (1,2), Yvan Josse (2), Viet Bac Le (2)

(1) Spoken Language Processing Group, CNRS-LIMSI; (2) Vocapia Research;
Orsay, France

This paper presents initial work in transcribing conversational telephone speech in Russian. Acoustic seed models were derived from other languages. The initial studies are carried out with 9 hours of transcribed data, and explore the choice of the phone set and use of other data types to improve transcription performance. Discriminant features produced by a Multi Layer Perceptron trained on a few hours of Russian conversational data are contrasted with those derived from well-trained networks for English telephone speech and from Russian broadcast data. Acoustic models trained on broadcast data filtered to match the telephone band achieve results comparable to those obtained with models trained on the small conversation telephone speech corpus.

Full Paper

Bibliographic reference.  Lamel, Lori / Courcinous, Sandrine / Gauvain, Jean-Luc / Josse, Yvan / Le, Viet Bac (2012): "Transcription of Russian conversational speech", In SLTU-2012, 156-161.