In this paper an uncertainty weighting scheme for DNNHMM-based speech recognition is proposed to increase discriminability in the decoding process. To this end, the DNN pseudo-log-likelihoods are weighted according to the ...

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, ...

A speech enhancement algorithm improves the perceptual aspects of a speech degraded by noise signals. We propose a phase-aware deep neural network (DNN) using the regularized sparse features for speech enhancement. A ...

In this paper an uncertainty weighting scheme for DNNHMM-based speech recognition is proposed to increase discriminability in the decoding process. To this end, the DNN pseudo-log-likelihoods are weighted according to the ...

This article conducts the study of the algorithms and methods used for automatic speech recognition. The importance of its application lies in improving the learning process taking into account characteristics such as ...

En esta tesis se describe las modificaciones a la parametrización de bancos de filtros normalizados localmente que mejoran sustancialmente su rendimiento en la tarea de reconocimiento robusto de voz en la base de datos ...