Robust speech recognition in noisy and reverberant environments using deep neural network-based systems
Doctor en Ingeniería Eléctrica === In this thesis an uncertainty weighting scheme for deep neural network-hidden Markov model (DNN-HMM) based automatic speech recognition (ASR) is proposed to increase discriminability in the decoding process. To this end, the DNN pseudo-log-likelihoods are weighted...
Main Author: | |
---|---|
Other Authors: | |
Language: | en |
Published: |
Universidad de Chile
2019
|
Subjects: | |
Online Access: | http://repositorio.uchile.cl/handle/2250/168062 |