NTT- - Speech enhancement front-end for robust automatic speech recognition with large amount of training data

Parametrizace s obohacováním řeči pro robustní automatické rozpoznávání řeči s velkým objemem trénovacích dat

contract

speech recognition, robustness, large data, DNN embeddings

The purpose of the Joint Research is to develop Speech enhancement front-end for robust automatic speech recognition with large amount of training data through the cooperation of NTT and BUT. The work is relying on embeddings produced by neural networks in various places of the processing chain.

Černocký Jan, prof. Dr. Ing. (UPGM FIT VUT) , research leader
Žmolíková Kateřina, Ing., Ph.D. (UPGM FIT VUT) , team leader
Baskar Murali K. (UPGM FIT VUT)
Kocour Martin, Ing. (UPGM FIT VUT)
Pavlus Ján, Ing. (UPGM FIT VUT)
Szőke Igor, Ing., Ph.D. (UPGM FIT VUT)
Švec Ján, Ing. (UPGM FIT VUT)
Veselý Karel, Ing., Ph.D. (UPGM FIT VUT)