Martin Zelenák
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Martin Zelenák has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Carlos Segura
Herta Secur, Barcelona, Spain
1 shared publication Henrik Schulz
TALP Research Center, Department of Signal Theory and Communications, Universitat Politècnica de Catalunya, C/Jordi Girona 1-3, 08034 Barcelona, Spain
1 shared publicationJavier Hernando
TALP Research Center, Department of Signal Theory and Communications, Universitat Politècnica de Catalunya, C/Jordi Girona 1-3, 08034 Barcelona, Spain
1 shared publication- Javier Hernando
Department of Signal Theory and Communications, Universitat Politècnica de Catalunya, Barcelona, Spain
1 shared publication - Jordi Luque
Telefonica Research Spain
1 shared publication
Latest Publications
- Open Access
- 31 July 2012
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2012 (1) , 19
Speaker diarization of broadcast news in Albayzin 2010 evaluation campaign
- 31 July 2012
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2012 (1) , 19
Open AccessSpeaker diarization of broadcast news in Albayzin 2010 evaluation campaign
- 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.