14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

BUT BABEL System for Spontaneous Cantonese

Martin Karafiát, František Grézl, Mirko Hannemann, Karel Veselý, Jan Černocký

Brno University of Technology, Czech Republic

This paper presents our work on speech recognition of Cantonese spontaneous telephone conversations. The key-points include feature extraction by 6-layer Stacked Bottle-Neck neural network and using fundamental frequency information at its input. We have also investigated into robustness of SBN training (silence, normalization) and shown an efficient combination with PLP using Region-Dependent transforms. A combination of RDT with another popular adaptation technique (SAT) was shown beneficial. The results are reported on BABEL Cantonese data.

Full Paper

Bibliographic reference.  Karafiát, Martin / Grézl, František / Hannemann, Mirko / Veselý, Karel / Černocký, Jan (2013): "BUT BABEL system for spontaneous Cantonese", In INTERSPEECH-2013, 2589-2593.