Dr.Itshak Lapidot

Staff

Academic Background

Itshak Lapidot received his B.Sc., M.Sc., and Ph.D. degrees from the Electrical and Computer Engineering Department, Ben-Gurion University, Beer-Sheva. He held a postdoctoral position at IDIAP Switzerland. Dr. Lapidot was previously a lecturer at the Electrical and Electronics Engineering Department at Sami Shamoon College of Engineering (SCE), in Beer-Sheva, Israel and served as a Researcher at the Laboratoire Informatique d'Avignon (LIA), University of Avignon in France. Recently, Dr. Lapidot assumed a teaching position with the Electrical Engineering Department at the Afeka Academic College of Engineering and joined the ACLP research team. 

Professional Background

Dr. Lapidot's primary research interests are speaker diarization and speaker verification. He is also interesting in clustering and time series analysis from theoretical point of view.

Teaching

Introduction to Signals and Systems
Introduction to random processes
Random Signals Processing
Electrical Engineering 1
Introduction to Electrical and Electronics Engineering
Linear Systems

Reasrearch 

Magneton with NICE on Speaker diarization
Working on Speaker verification and clustering
Cooperation with Sami-Shamun Colege of Engineering, Ben-Gurion University and Soroka Hospital on Classification of microorganisms using vibrational spectroscopy.

Publications

Chapters in Books

[1]I. Lapidot (Voitovetsky) and H. Guterman, “VQ-based clustering algorithm of piecewise-dependent-data,” in Advances in Self-Organising Maps, N. Allison, H. Yin, L. Allison and J. Slack Eds. Springer, 2001, pp.95-101.

 
Refereed Journal Papers

[1]A. Salman, A. Pomerantz, L. Tsror, I. Lapidot, R. Moreh, S. Mordechai, and M. Huleihel, “Utilizing FTIR-ATR spectroscopy for classification and relative spectral similarity evaluation of different Colletotrichum coccodes isolates, ” Analyst, vol. 137, no. 15, pp. 3558-3564, 2012.

[2]A. Salman, I. Lapidot, A. Pomerantz, L. Tsror, Z. Hammody, R. Moreh, M. Huleihel, and S. Mordechai, “Detection of Fusarium oxysporum Fungal Isolates Using ATR Spectroscopy, ” Spectroscopy: An International Journal, vol. 27, no. 5-6, pp. 551-556, 2012.

[3]O. Ben-Harush, O. Ben-Harush, I. Lapidot, and H. Guterman, “Initialization of iterative-based speaker diarization for telephone conversations,” IEEE Trans. on Audio, Speech, and Language Processing, vol. 20, no. 2, pp. 414-425, February 2012.

[4]A.Salman, I. Lapidot, A. Pomerantz, L. Tsror, E. Shufan, R. Moreh, S. Mordechai and M. Huleihel, “Identification of fungal phytopathogens using FTIR-ATR spectroscopy and advanced statistical methods,” Journal of Biomedical Optics, vol. 17, no.1, 2012.

[5]A. Pomerantz1, A. Salman, L. Tsror, I. Lapidot, A. Zwielly, R. Moreh, S. Mordechai, and M. Huleihel, “Detection and identification of Fusarium oxysporum strains using FTIR-ATR spectroscopy,” Analyst, vol. 136,no. 5, pp. 988-995, 2011.

[6]I. Lapidot and H. Guterman, “Dichotomy Between Clustering Performance and Minimum Distortion in Piecewise-Dependent-Data (PDD) Clustering,” IEEE Signal Processing Letters, vol. 10, no. 4, pp. 98-100, April 2003.

[7]I. Lapidot (Voitovetsky), H. Guterman, and A. Cohen, “Unsupervised speaker recognition based on competition between self-organizing maps,” IEEE Trans. on Neural Networks, vol. 13, no. 4, pp. 877-887, July 2002.

 

Refereed Conference Papers

[1]A. Salman, I. Lapidot, E. Shufan and M. Huleihel, “Differentiation of Mixed Bacteria Samples in the Generic and Species Levels Using Infrared Spectroscopy and Multivariate Analysis,“ IEEE 28th Convention of Electrical and Electronics Engineers in Israel, 2014, Eilat, Israel.

[2]T. Furmanov, L. Aminov, A. Moyal, and I. Lapidot, “Randomization Effect on Iterative-Based Speaker Diarization System for Telephone Conversations,“ IEEE 28th Convention of Electrical and Electronics Engineers in Israel, 2014, Eilat, Israel.

[3]T. Furmanov, L. Aminov, A. Moyal, and I. Lapidot, “Mahalanobis Based Emission Model for Speaker Diarization of Telephone Conversations,“ IEEE 28th Convention of Electrical and Electronics Engineers in Israel, 2014, Eilat, Israel.

[4]I. Lapidot, L. Aminov, T. Furmanov, and A. Moyal “Speaker Diarization in Commercial Calls,“ Speech Processin Conference, July 7-8, 2014, Afeka Tel-Aviv, Israel.

[5]I. Lapidot, J.-F. Bonastre, and S. Bengio, “Telephone Conversation Speaker Diarization Using Mealy-HMMs,” Speaker Odyssey 2014, June 16-19, Finland.

[6]I. Lapidot and J.-F. Bonastre,Integration of LDA into speaker diarization system, 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, November 14-17, 2012, Eilat, Israel.

[7]I. Lapidot, Initial conditions for telephone conversations diarization system, 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, November 14-17, 2012, Eilat, Israel.

[8]A. Salman, I. Lapidot, A. Pomerantz, L. Tsror, R. Moreh, S. Mordechai, and M. Huleihel,“Using FTIR-ATR spectroscopy and PCA calculation to develop spectral similarity algorithm of Phyto-Pathogenes isolats,” 31st European Congress on Molecular Spectroscopy, 26-31 August, 2012, Cluj-Napoca, Romania.

[9]I. Lapidot and J.-F. Bonastre, “Generalized Viterbi-based models for time-series segmentation applied to speaker diarization,” Odyssey2012, June 25-28, 2012, Singapore.

[10]   I. Lapidot and J.-F. Bonastre, “Optimizing feature representation for speaker diarization using PCA and LDA,” Speech Processing Conference, June 19-20, 2012, Tel-Aviv, Israel.

[11]   I. Lapidot and H. Guterman, “Future challenges in speaker diarization,” Speech Processing Conference, June 21-22, 2011, Tel-Aviv, Israel.

[12]   U. Ben Simon, I. Lapidot, and H. Guterman, “Comparison between Normalizations for SVM – GMM Supervectors Speaker Verification,” 2010 IEEE-26th Convention of Electrical and Electronics Engineers in Israel, November 17-20, 2010, Eilat, Israel.

[13]   W. Abo-Gannemhy, I. Lapidot, and H. Guterman, “Speech Recognition using Combined Forward and Backward Viterbi Search,” 2010 IEEE-26th Convention of Electrical and Electronics Engineers in Israel, November 17-20, 2010, Eilat, Israel.

[14]   O. Ben-Harush, I. Lapidot, and H. Guterman, “Incremental diarization of telephone conversations,” Interspeech’10, September 26-30, 2010, Kaihin Makuhari, Japan.

[15]   O. Ben-Harush, I. Lapidot, and H. Guterman, “Online diarization of telephone conversations,” Odyssey’10, June 28 – July 01, 2010, Brno, Czech.

[16]   O. Ben-Harush, I. Lapidot, and H. Guterman, “Entropy based overlapped speech detection as a pre-processing stage for speaker diarization,” Interspeech’09, September 6-10, 2009, Brighton, UK.

[17]   O. Ben-Harush, I. Lapidot, and H. Guterman, “Frame level entropy based overlapped speech detection as a pre-processing stage for speaker diarization,” MLSP’09, September 2-4, 2009, Grenoble, France.

[18]   O. Ben-Harush, I. Lapidot, and H. Guterman, "Pure Segments Selection as Speaker Clustering Post-Processing," 2008 IEEE-25th Convention of Electrical and Electronics Engineers in Israel, December 3-5, 2008, Eilat, Israel.

[19]   O. Ben-Harush, I. Lapidot, and H. Guterman, "Weighted segmental K-means initialization for SOM-based speaker clustering," Interspeech-2008,September 22-26, 2008, Brisbane, Australia.

[20]   O. Ben-Harush, I. Lapidot, and H. Guterman, "Segmental K-means initialization for SOM-based speaker clustering," ELMAR-2008, September 10-13, 2008, Zadar, Croatia.

[21]   I. Lapidot, “SOM as Likelihood Estimator for Speaker Clustering,” Proc. Eurospeech’03, pp. 3001-3004, September 1-4, 2003, Geneva, Switzerland.

[22]   J. Ajmera, H. Bourlard, I. Lapidot, and I. McCowan, “Unknown-multiple speaker clustering using HMM,” Proc. International Conference on Spoken Language Processing, pp. 573-576, September 16-20, 2002, Denver, Colorado, USA.

[23]   I. Lapidot and H. Guterman, “Resolution limitation in speakers clustering and segmentation problems,” 2001: A Speaker Odyssey, The Speaker Recognition Workshop, pp. 169-173, June 18-22, 2001, Crete, Greece.

[24]   I. Voitovetsky, H. Guterman, and A. Cohen, “Validity criterion for unsupervised speaker recognition,” Proceedings of the First Workshop on Text Speech, and Dialogue, pp. 321-326, September 1998, Brno, Czech Republic.

[25]   I. Voitovetsky, H. Guterman, and A. Cohen, “Unsupervised speaker classification using self-organizing maps (SOM),” Neural Networks for Signal Processing VII Proceedings of the 1997 IEEE Workshop, pp. 578-587, September 1997, Amalia Island, USA.

[26]   I. Voitovetsky and H. Guterman, “Encoding resolution in Hopfield associative memory networks,” The 18th Convention of Electrical and Electronics Engineers in Israel, pp. 4.3.2.1-4, March 1995, Tel-Aviv, Israel.

[27]   I. Voitovetsky, S. Dahan, Y, Menashe and H. Guterman, “Speaker independent vowel recognition using neural networks,” Proc. the 10th Israeli Symposium on Artificial Intelligence Computer Vision and Neural Networks, pp. 177-183, December 1993, Tel-Aviv, Israel.

 

Scientific Technical Reports

[1]I. Lapidot, “Self-Organizing-Maps with BIC for speaker clustering,” IDIAP-RR-02-60, December 2002.

[2]I. Lapidot, “What is better: GMM of two Gaussians or two clusters with one Gaussian?” IDIAP-RR-02-56, November 2002.

[3]I. Lapidot and H. Guterman, “Dichotomy Between Clustering Performance and Minimum Distortion in Piecewise-Dependent-Data (PDD) Clustering,” IDIAP-RR-02-48, October 2002.

[4]I. Lapidot and A. Morris, “Extended BIC criterion for model selection,” IDIAP-RR-02-42, October 2002.

[5]J. Ajmera, H. Bourlard, and I. Lapidot, “Improved unknown-multiple speaker clustering using HMM,” IDIAP-RR-02-23, August 2002.

[6]J. Ajmera, H. Bourlard, I. Lapidot, and I. McCowan “Unknown-multiple speaker clustering using HMM,” IDIAP-RR-02-07, April 2002.