activity
20172019
most citedMultichannel Robot Speech Recognition Database: MChRSR

1 citations · 2 across the 4 of their papers we have counts for

collaborators

6 papers

eess.AS2019

On combining features for single-channel robust speech recognition in reverberant environments

José Novoa, Josué Fredes, Jorge Wuth +3

This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberan…

eess.AS20191 cited

Weighted delay-and-sum beamforming guided by visual tracking for human-robot interaction

José Novoa, Rodrigo Mahu, Alejandro Díaz +3

This paper describes the integration of weighted delay-and-sum beamforming with speech source localization using image processing and robot head visual servoing for source tracking…

eess.AS2018

An improved DNN-based spectral feature mapping that removes noise and reverberation for robust automatic speech recognition

Juan Pablo Escudero, José Novoa, Rodrigo Mahu +4

Reverberation and additive noise have detrimental effects on the performance of automatic speech recognition systems. In this paper we explore the ability of a DNN-based spectral f…

eess.AS2018

Exploring the robustness of features and enhancement on speech recognition systems in highly-reverberant real environments

José Novoa, Juan Pablo Escudero, Jorge Wuth +4

This paper evaluates the robustness of a DNN-HMM-based speech recognition system in highly-reverberant real environments using the HRRE database. The performance of locally-normali…

cs.HC20171 cited

Multichannel Robot Speech Recognition Database: MChRSR

José Novoa, Juan Pablo Escudero, Josué Fredes +3

In real human robot interaction (HRI) scenarios, speech recognition represents a major challenge due to robot noise, background noise and time-varying acoustic channel. This docume…

cs.SD2017

DNN-based uncertainty estimation for weighted DNN-HMM ASR

José Novoa, Josué Fredes, Néstor Becerra Yoma

In this paper, the uncertainty is defined as the mean square error between a given enhanced noisy observation vector and the corresponding clean one. Then, a DNN is trained by usin…