Josué Fredes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Josué Fredes has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Richard M. Stern
Department of Electrical and Computer Engineering and Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publicationsSimon King
Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K.
2 shared publications- Víctor Poblete
Austral University of Chile
2 shared publications Felipe Espic
Univ Chile, Dept Elect Engn, Speech Proc & Transmiss Lab, Santiago, Chile
1 shared publication- Fernando Huenupan
Departamento de Ingeniería Eléctrica, Facultad de Ingeniería y Ciencias, Universidad de La Frontera
1 shared publication - Javier Ruiz-Del-Solar
University of Chile
1 shared publication
Latest Publications
- 31 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (4) , 377-381
Locally Normalized Filter Banks Applied to Deep Neural-Network-Based Robust Speech Recognition
This letter describes modifications to locally normalized filter banks (LNFB), which substantially improve their performance on the Aurora-4 robust speech recognition task using a Deep Neural Network-Hidden Markov Model (DNN-HMM)-based speech recognition system. The modified coefficients, referred to as LNFB features, are a filter-bank version of locally normalized cepstral coefficients (LNCC), which have been described previously. The ability of the LNFB features is enhanced through the use of newly proposed dynamic versions of them, which are developed using an approach that differs somewhat from the traditional development of delta and delta-delta features. Further enhancements are obtained through the use of mean normalization and mean-variance normalization, which is evaluated both on a per-speaker and a per-utterance basis. The best performing feature combination (typically LNFB combined with LNFB delta and delta-delta features and mean-variance normalization) provides an average relative reduction in word error rate of 11.4% and 9.4%, respectively, compared to comparable features derived from Mel filter banks when clean and multinoise training are used for the Aurora-4 evaluation. The results presented here suggest that the proposed technique is more robust to channel mismatches between training and testing data than MFCC-derived features and is more effective in dealing with channel diversity.
- 31 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (4) , 377-381
Locally Normalized Filter Banks Applied to Deep Neural-Network-Based Robust Speech Recognition
This letter describes modifications to locally normalized filter banks (LNFB), which substantially improve their performance on the Aurora-4 robust speech recognition task using a Deep Neural Network-Hidden Markov Model (DNN-HMM)-based speech recognition system. The modified coefficients, referred to as LNFB features, are a filter-bank version of locally normalized cepstral coefficients (LNCC), which have been described previously. The ability of the LNFB features is enhanced through the use of newly proposed dynamic versions of them, which are developed using an approach that differs somewhat from the traditional development of delta and delta-delta features. Further enhancements are obtained through the use of mean normalization and mean-variance normalization, which is evaluated both on a per-speaker and a per-utterance basis. The best performing feature combination (typically LNFB combined with LNFB delta and delta-delta features and mean-variance normalization) provides an average relative reduction in word error rate of 11.4% and 9.4%, respectively, compared to comparable features derived from Mel filter banks when clean and multinoise training are used for the Aurora-4 evaluation. The results presented here suggest that the proposed technique is more robust to channel mismatches between training and testing data than MFCC-derived features and is more effective in dealing with channel diversity.
- 1 May 2015
- Published by Elsevier in Computer Speech & Language
- Vol. 31 (1) , 1-27
A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification
- 1 May 2015
- Published by Elsevier in Computer Speech & Language
- Vol. 31 (1) , 1-27
A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification
- 1 January 2008
- Published by Springer Nature
- p. 246-253
Automatic On-Line Color Calibration Using Class-Relative Color Spaces
- 1 January 2008
- Published by Springer Nature
- p. 246-253
Automatic On-Line Color Calibration Using Class-Relative Color Spaces