Javier Hernando
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Javier Hernando has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Pascual Ejarque2 shared publications
- Ainara Garde
Dep. of ESAII, Centre for Biomedical Engineering Research, Technical University of Catalonia (UPC), c./ Gargallo, 5, 08028, Barcelona, Spain
1 shared publication - Ainara Garde
Talp Research Center, Department of Signal Theory and Communications, Technical University of Catalonia, Barcelona, Spain
1 shared publication - Albert Ali Salah
Information and Computing Sciences, Utrecht University, Utrecht, Netherlands
1 shared publication - Ben Schouten
Centre for Mathematics and Computer Science
1 shared publication - Carlos Segura
Telefónica Scientific Research Barcelona Spain
1 shared publication
Latest Publications
- 23 January 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 20 (2) , 436-446
Simultaneous Speech Detection With Spatial Features for Speaker Diarization
Simultaneous speech poses a challenging problem for conventional speaker diarization systems. In meeting data, a substantial amount of missed speech error is due to speaker overlaps, since usually only one speaker label per segment is assigned. Furthermore, simultaneous speech included in training data can lead to corrupt speaker models and thus worse segmentation performance. In this paper, we propose the use of three spatial cross-correlation-based features together with spectral information for speaker overlap detection on distant microphones. Different microphone-pair data are fused by means of principal component analysis. We have obtained an improvement of the speaker diarization system over the baseline by discarding overlap segments from model training and assigning two speaker labels to them according to likelihoods in Viterbi decoding. In experiments conducted on the AMI Meeting corpus, we achieve a relative DER reduction of 11.2% and 17.0% for single- and multi-site data, respectively. The improvement of clustering with techniques such as beamforming and TDOA-feature stream also leads to a higher effectiveness of the overlap labeling algorithm. Preliminary experiments with NIST RT data show DER improvement on the RT'09 meeting recordings as well.
- 23 January 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 20 (2) , 436-446
Simultaneous Speech Detection With Spatial Features for Speaker Diarization
Simultaneous speech poses a challenging problem for conventional speaker diarization systems. In meeting data, a substantial amount of missed speech error is due to speaker overlaps, since usually only one speaker label per segment is assigned. Furthermore, simultaneous speech included in training data can lead to corrupt speaker models and thus worse segmentation performance. In this paper, we propose the use of three spatial cross-correlation-based features together with spectral information for speaker overlap detection on distant microphones. Different microphone-pair data are fused by means of principal component analysis. We have obtained an improvement of the speaker diarization system over the baseline by discarding overlap segments from model training and assigning two speaker labels to them according to likelihoods in Viterbi decoding. In experiments conducted on the AMI Meeting corpus, we achieve a relative DER reduction of 11.2% and 17.0% for single- and multi-site data, respectively. The improvement of clustering with techniques such as beamforming and TDOA-feature stream also leads to a higher effectiveness of the overlap labeling algorithm. Preliminary experiments with NIST RT data show DER improvement on the RT'09 meeting recordings as well.
- Open Access
- 29 May 2008
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 2 (2) , 75-91
Multimodal identification and localization of users in a smart environment
- 29 May 2008
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 2 (2) , 75-91
Open AccessMultimodal identification and localization of users in a smart environment
- 1 January 2007
- Published by Springer Nature in Annals of Telecommunications
- Vol. 62 (1-2) , 109-129
On the use of genuine-impostor statistical information for score fusion in multimodal biometrics/sur l’usage de l’information statistioue client-imposteur pour la fusion des scores en biométrie multimodale
- 1 January 2007
- Published by Springer Nature in Annals of Telecommunications
- Vol. 62 (1-2) , 109-129
On the use of genuine-impostor statistical information for score fusion in multimodal biometrics/sur l’usage de l’information statistioue client-imposteur pour la fusion des scores en biométrie multimodale
- 1 January 2007
- Published by INSTICC
- p. 33-38
ON THE EFFECT OF SCORE EQUALIZATION IN SVM MULTIMODAL BIOMETRIC SYSTEMS
- 1 January 2007
- Published by INSTICC
- p. 33-38
ON THE EFFECT OF SCORE EQUALIZATION IN SVM MULTIMODAL BIOMETRIC SYSTEMS
- 1 January 2006
- Published by INSTICC
- p. 17-23
PERSON VERIFICATION BY FUSION OF PROSODIC, VOICE SPECTRAL AND FACIAL PARAMETERS
- 1 January 2006
- Published by INSTICC
- p. 17-23
PERSON VERIFICATION BY FUSION OF PROSODIC, VOICE SPECTRAL AND FACIAL PARAMETERS