Address: Department of Electrical Engineering College of Engineering American University of Sharjah P.O.Box 26666 Sharjah, United Arab Emirates Room: EL118 Office: +(971) (6) 5152917 Fax: +(971) (6) 5152979 E-mail: kassaleh@aus.edu

Research Interests

Robust speech and speaker recognition, pattern classification, speech enhancement, and image processing.

Biography

Dr. Assaleh joined the Department of Electrical Engineering in fall 2002. Prior to August 2002, Dr. Assaleh had a nine-year career in research and development after he completed his PhD in 1993 from Rutgers , The State University of New Jersey. From March 1997 to July 2002, he was with Conexant Systems Inc (formerly Rockwell Semiconductor Systems) in Newport Beach , California . He was a group leader of engineering with the wireless communications division where he led and directed projects related to speech recognition, speech enhancement including acoustic noise and echo cancellation. From March 1997 to December 2000, he was with the Network Access Division as a senior staff engineer where he worked on application of speech processing and recognition for voice over IP, central site modem, and fax engines. Prior to that, Dr. Assaleh was a senior staff engineer with Motorola Inc. in Phoenix from November 1994 to March 1997 where he was a member of the speech and signal processing lab. He was involved in several projects at Motorola in the secure communications area. Dr. Assaleh won the Motorola Engineering Award in 1996. From October 1993 to November 1994, Dr. Assaleh was a research professor at the Center for Computer Aid and Industrial Productivity (CAIP), Rutgers University . As a research professor, Dr. Assaleh was an associate investigator for several government funded projects in the area of secure access control using speaker authentication. Throughout his research as a PhD candidate, Dr. Assaleh 's work was funded by USAF, DoD, and other US governmental agencies. His PhD research was the nucleus of the Speak-EZ technology for speaker authentication.

Dr. Assaleh holds 10 US patents and has published more than 35 research papers in fields related to signal processing and pattern recognition. He is a senior member of the IEEE and a member of the IEEE Signal Processing Society. He is a regular reviewer for several IEEE journals and conferences. He was appointed as the technical chairman of the International Symposium of Signal Processing and its Applications in 1999 (ISSPA'99). He has also served as session chair and technical committee member in various IEEE international conferences. He was appointed as the Signal and Image Processing track leader of the 2004 Second IEEE GCC conference. Dr. Assaleh has been appointed as the Technical Chair of the 2007 International Symposium of Signal Processing and its Applications. He is also a cofounder and a steering committee member of the AUS International Symposium on Mechatronics (AUS-ISM) since 2003.

Publications

Patents

1. User configurable levels of security for a speaker verification system, U.S. patent number 6,691,089 (issued 2/10/2004), Su, Huan-Yu, and Assaleh Khaled.
2. Low complexity speaker verification using simplified hidden markov models with universal cohort models and automatic score thresholding, U.S. patent number 6,556,969 (issued 4/29/2003) Assaleh, Khaled and Ayman Asadi.
3. Access Control System and Method Therefor, U.S. patent number 6,243,695 (issued 6/5/2001) Assaleh, Khaled, and Campbell, William.
4. USER CONFIGURABLE LEVELS OF SECURITY FOR A SPEAKER VERIFICATION European Patent number [_] WO0123982 (issued 4/5/2001) ASSALEH KHALED; and SU, Huan Yu
5. Multiresolutional classifier with training system and method, U.S. patent number 6,192,353 (issued 2/20/2001), Assaleh, K. T., W. M. Campbell, and J. E. Kleider.
6. Speaker independent speech recognition system and method U.S. patent number 5,946,653, (issued 8/31/1999) Campbell, W. M., J. E. Kleider, C. C. Broun, S. E. Gifford, and K. T. Assaleh.
7. Speaker Identification System and Method, U.S. patent number 5,930,748 (issued 7/27/1999), Kleider, J. E., and Assaleh, K. T.
8. Method and apparatus for training a speaker recognition system, U.S. patent number 5,864,807 (issued 1/26/1999), Campbell, William, and Assaleh, Khaled.
9. Speaker verification system using decision fusion logic, U.S. patent number 5,839,103 (issued 11/17/1998), Mammone; Richard J., Farrell; Kevin Sharma; Manish, Naik; Devang, Zhang; Xiaoyu, Assaleh; Khaled, T. and Liou; Han-Seng
10. Speaker Identification and Verification System” U.S. patent number 5,522,012 (issued 5/28/1996), Richard J. Mammone and Khaled T. Assaleh.
11. An Endpoint Detection of Speech for Improved Speech Recognition in Noisy Environments, 00CXT0717N (Filed to the US patent office), S. Bou-Ghazale, A. Asadi, and K. Assaleh.
12. Separating Mixed Signals, US11/189,677 (Filed to the US patent office), Khaled Assaleh and Hasan Al-Nashash .
    
    Journal and Conference Papers
    
13. Extraction of Fetal Electrocardiogram Using Adaptive Neuro-Fuzzy Inference Systems. Khaled Assaleh. Accepted for publication in the IEEE Transactions on Biomedical Engineering, June 2006.
14. A Novel Technique for the Extraction of Fetal ECG Using Polynomial Networks, Khaled Assaleh, and Hasan Al-Nashash, IEEE Transactions on Biomedical Engineering, Volume 52, no. 6, pages: 1148 –1152, June 2005.
15. Feature Extraction and Analysis for Classifiying Causable Patterns in Control Charts, Khaled Assaleh and Yousef Alassaf, Computers & Industrial Engineering Journal, Volume 49, Issue 1, August 2005, pages 168-181.
16. Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers, Khaled Assaleh and M. Al-Rousan, EURASIP Journal on Applied Signal Processing, Volume 2005, Issue 13, pages: 2136-2146, August 2005.
17. Speaker Recognition with Polynomial Classifiers, W. M. Campbell, Khaled Assaleh, and Charles C. Broun, IEEE Transactions on Speech and Audio Processing, Volume 10 Issue 4, May 2002.
18. New LP-Derived Features for Speaker Identification, Assaleh, K. T. and Mammone, R. J. , IEEE Transactions. on Speech and Audio Processing, Volume 2, Number 4, pages 630-638, 1994.
19. Speaker Recognition using Neural Networks and Conventional Classifiers, K.R. Farrell , R. J. Mammone , and K.T. Assaleh , IEEE Transactions on Speech and Audio Processing, Volume 2, Number 1, part II, page 194-205, January 1994.
20. Adaptive Neuro-fuzzy Inference Systems for Extracting Fetal Electrocardiogram, Khaled Assaleh , Proceedings of the Sixth IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2006), Vancouver, Canada, August, 2006.
21. Online Arabic Isolated Letter Recognition Using Two-Tier DTW Classifier, G. Alhabian and K. Assaleh, the 10th World Multiconference on Systemics, Cybernetics and Informatics (SCI 2004), Orlando, USA, July 2006.
22. Smart Voice-driven Wheelchair, M. AlRousan , K. Assaleh , and L. Tawalbeh , Third AUS International Symposium on Mechatronics AUS-ISM06 , April 2006.
23. Online video-based handwritten Arabic alphabet recognition, K. Assaleh, T. Shanableh, and H. Hajjaj, Third AUS International Symposium on Mechatronics AUS-ISM06, April 2006.
24. Spectral Subtraction and Cepstral Distance for Enhancing EEG Entropy, Assaleh, Khaled and Al-Nashash, Hasan, Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, September 2005.
25. Automated Remote Measurements in Industrial Settings, A. Gabir , A. Fawzi , K. Assaleh , and H. Al-Nashash , Second AUS International Symposium on Mechatronics AUS-ISM05 , April 2005.
26. The Application of Polynomial Discriminant Function Classifiers to Isolated Arabic Speech Recognition, M. Khasawneh, Khaled Assaleh , and Wesam Sweidan, Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), Budpest, Hungary, July 2004.
27. Handwritten Arabic Character Recognition Using Co-occurrence Matrices", Khaled Assaleh , Mohammed Al-Rousan, and Mohammaed Ghazal, Proceedings of the Eighth World Multiconference on Systemics, Cybernetics and Informatics (SCI 2004), Orlando, USA, July 2004.
28. Online Recognition of Handwritten Arabic Characters for PDAs, Mohammed GHAZAL , Khaled ASSALEH , and Mohammed AL-ROUSAN , International Conference on Computational Intelligence (ICCI 2004), Lefkoşa, North Cyprus , May 2004.
29. Non-Iterative Method for Two-Lead Fetal ECG Extraction, Assaleh, Khaled and Al-Nashash, Hasan, 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Francisco, September 2004.
30. Fusion of Multiple Feature Sets for Automatic Face Recognition, K. Assaleh and S. Sagali, Proceedings of the Second IEEE GCC Conference, Bahrain, November 2004.
31. A Robust Endpoint Detection of Speech for Noisy Environments with Application to Automatic Speech Recognition, Sahar Bou-Ghazale and Khaled Assaleh, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2002), Orlando, Florida, April 2002.
32. A Novel Algorithm for Training Polynomial Networks, W. M. Campbell, Khaled Assaleh, and C. C. Broun, International NAISO Symposium on Information Science Innovations ISI’2001, Dubai, UAE, March 2001.
33. Speaker Identification Using a Polynomial-based Classifier, K. T. Assaleh and W. M. Campbell, International Symposium on Signal Processing and its Applications ISSPA’99, Brisbane, Australia, August 1999.
34. Low-Complexity Small-Vocabulary Speech Recognition for Portable Devices, W. M. Campbell and Khaled Assaleh, International Symposium on Signal Processing and its Applications ISSPA’99, Brisbane, Australia, August 1999.
35. Audio Sensors and Low-Complexity Recognition Technologies for Soldier Systems W. Campbell, K. T. Assaleh, and C. Broun SPIE, Volume 3394, Orlando, 1999
36. Polynomial classifier Techniques for Speaker Verification, W. M. Campbell and K. T. Assaleh, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’ 99) Phoenix, March, 1999
37. Automatic Evaluation Of Speaker Recognizability Of Coded Speech, Khaled T. Assaleh, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’96) Volume 1, Page 475, Atlanta, 1996.
38. Hyperspectral Image Coding using Trellis Coded Quantization, Glen Abousleman and Khaled Assaleh, International Conference on Information Systems, Analysis, and Synthesis (ISAS), Orlando 1996.
39. Motorola Advanced excitation Model (MAXM) Vocoder, C. Bergstrom, K. Assaleh, International Symposium on Signal Processing and its Applications ISSPA, The Gold Coast, Queensland, Australia, 1996.
40. Supplementary Orthogonal Cepstral Features, Khaled T. Assaleh., IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Volume 1, Page 413, Detroit, 1995
41. Robust Cepstral Features for Speaker Identification, Khaled T. Assaleh and Richard J. Mammone , IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’94) Volume 1, Page 129, Adelaide , Australia , 1994
42. Robust Speaker Identification Using Pole Filtering, Naik, D. and Assaleh, K. and Mammone R., ESCA Workshop on Speaker Recognition, Identification, and Verification, page 225-228, Switzerland , 1994
43. Text-Dependent Speaker Verification Using Data Fusion and Channel Detection, Assaleh, Khaled T.; Farrell, Kevin R.; Zilovic, M. S.; Sharma, Manish; Naik, Devang K.; Mammone, Richard J., SPIE, vol. 2277, p. 72-82, San Diego, August, 1994
44. Speech Recognition Using the Modulation Model, K. Assaleh , R. Mammone , Mazin G. Rahim and J Flanagan , IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’93) Volume 2, Page 664, Minneapolis , Minnesota , 1993
45. Signal-Adaptive Decomposition of Multicomponent Signals, Assaleh, Khaled T.; Mammone, Richard J., SPIE, Volume 2027, pages 269-27, San Diego, 1993
46. Speaker Recognition Using the Neural Tree Network, Farrell, Kevin R.; Assaleh, Khaled T.; Mammone, Richard J., SPIE, Volume 2093, pages 20-31, Innsbruck, Austria, Oct, 1993
47. A New Method of Modulation Classification for Digitally Modulated Signals, Khaled Assaleh, Kevin Farrell, and Richard Mammone, IEEE MILCOM, San Diego, 1992.
48. Spectral-Temporal Decomposition of Multicomponent Signals, Khaled Assaleh, Richard Mammone, and Adam Fineberg, IEEE Sixth SP Workshop on SSAP, Victoria, Canada, 1992.
49. Instantaneous Bandwidth and Formant Bandwidth, Leon Cohen, Khaled Assaleh, and Adam Fineberg, IEEE Sixth SP Workshop on SSAP, Victoria, Canada, 1992.
50. On The Realization of the Zak-Gabor Representation of Images, Assaleh, Khaled T.; Zeevi, Yehoshua Y.; Gertner, Izidor, SPIE Proc. Visual Communications and Image Processing, Volume 1606, pages 532-540, Boston, 1991.

Public Technical Reports

1. RL-TR-96-42 A Modulation Model for Characterizing Speech Signals. Richard Mammone, Khaled Assaleh, Ravi Ramachandran, Mihailo Zilovic. Final Technical Report, March, 1996, Rome Laboratory, Air Force Material Command, Rome, New York.
2. TR-167 Open Set Speaker Identification Using the Modulation Model. R. Mammone, J. L. Flanagan, K. Assaleh, K. Farrell, H. Liou, R. Ramachandran, 10/14/93, CAIP Center, Rutgers University