This paper discusses a mixed parameterisation modelling method in a speaker independent Automatie Speech Recognition (ASR) system Tor Polish keywords. The goal of this project is to improve the recognition quality in Polish commands and instructions recognition system based on mel-frequency cepstrum coefficients (MFCC) modelling. In this project we studied the recognition quality using a mixed speech modelling consisting of MFCC and prosodic parameters. We experimentally showed that the mixed modelling yields belter recognition quality than a simple MFCC modelling.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.