Product Details
SW1: ASR asijského jazyka
Created: 2021
English title
SW1: ASR of Asian language
Type
software
License
not public
Authors
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Lehečka Jan, Ing., Ph.D. (WBU in Pilsen)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Šmídl Luboš, Ing., Ph.D. (WBU in Pilsen)
Švec Jan, Ing., Ph.D. (WBU in Pilsen)
Lehečka Jan, Ing., Ph.D. (WBU in Pilsen)
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT)
Šmídl Luboš, Ing., Ph.D. (WBU in Pilsen)
Švec Jan, Ing., Ph.D. (WBU in Pilsen)
Keywords
speech recognition
Description
Automatic speech recognition system of Asian language based on standard neural network training approaches. They were further extended by: data augmentation, mining/training from public resources and multilingual pre-training. It led into better performance in acoustically difficult environment. The resulting product is command line software using Docker container running in standard Linux or Windows distribution.
Projects
Research groups
Speech Data Mining Research Group BUT Speech@FIT (VZ SPEECH)
Departments
Department of Computer Graphics and Multimedia FIT BUT (DCGM FIT BUT)
University of West Bohemia in Pilsen (WBU in Pilsen)
University of West Bohemia in Pilsen (WBU in Pilsen)