Hemant Arjun Patil

 

Office Address
Associate Professor,
Room No.4103, Faculty Block-4,
Dhirubhai Ambani Institute of Information and
Communication Technology (DA-IICT),
Gandhinagar-382 007,
Gujarat, India.
 Tel: +91-79-30510650
 Email: [email protected], [email protected]

 

Education

 

Experience


Research Interest


Awards and Honours


List of Publications

[A] Theses

[1] Hemant A. Patil, Speaker Recognition in Indian Languages: A Feature Based Approach. Ph.D. Thesis, Department of Electrical Engineering, IIT Kharagpur, India, July 2005.

[2] Hemant A. Patil, Study of Wavelets and Filterbanks. M.E. Thesis, Department of Instrumentation Engineering, SGGSCE&T, SRTMU, Nanded, MS, India, March 2001.

 [B] Journals

       B.1) International

 [3] Hemant A. Patil and T. K. Basu, “Identifying phonetically similar languages using Teager energy based cepstrum,” special issue on “Frontiers of Language Processing and Information Retrieval for Asian Languages”, Engineering Letters, IAENG International Journal, Hong Kong, vol.16, no.1, 9 pages, March  2008.

[4] Hemant A Patil and T. K. Basu, “LP spectra vs. Mel spectra for identification of professional mimics in Indian languages”, in Int. J. Speech Tech. , IJST, Springer-Verlag, vol. 11, no.1,pp. 1-16, March 2008.

[5] Hemant A Patil and T. K. Basu, “Development of speech corpora for speaker recognition research and evaluation in Indian languages”, in Int. J. of Speech Tech., IJST,  Springer-Verlag, vol. 11, no.1, pp.17-32, March 2008.

 B.2) National

[6] Snehesh Mitra, Hemant A. Patil and T. K. Basu, “Polynomial classifier techniques for speaker identification in Indian languages,” in J. of Systems Science and  Engineering, PARITANTRA, vol. 10, no. 1, pp. 42-48, Nov. 2004.

 [C] Book Chapters

[7] Hemant A. Patil, “Cry Babies”: Using spectrographic analysis to assess neonatal health from an infant’s cry, submitted for possible publications in "Visions of Speech: Exploring New Voice Apps in Mobile Environments, Call Centers and Clinics",  Springer-Verlag, 2010.

[8] Hemant A. Patil and T. K. Basu, “The Teager energy based features for identification of identical twins in multilingual environment,” N.R. Pal et al. (Eds.):ICONIP 2004, Lecture Notes in Computer Science, LNCS, Springer-Verlag, Berlin Heidelberg, Germany, vol. 3316, pp. 333-337, 2004.

[9] Hemant A. Patil and T. K. Basu, “Design of cubic spline wavelet for open set speaker classification in Marathi,” Q. Huo et al. (Eds) ISCSLP 2006, Lecture Notes in Artificial Intelligence, LNAI, Springer-Verlag, Berlin Heidelberg, Germany, vol. 4274, pp. 126-137, 2006.

[10] Hemant A. Patil and T. K. Basu, “Cepstral domain Teager energy for identifying perceptually similar languages” in A. Ghosh et al. (Ed.), Premi, Lecture Notes in Computer Science, LNCS, Springer-Verlag, Berlin Heidelberg, Germany, vol. 4815, pp. 455-462, 2007.

[11] Hemant A. Patil and Keshab K. Parhi, “Variable length Teager energy based Mel cepstral features for identification of twins”  in S. Chaoudhury et al. (Eds) PReMI 2009, Lecture Notes in Computer Science, LNCS, Springer-Verlag, Berlin Heidelberg, Germany, vol. 5909,  pp. 525-530, 2009.

[12] Hemant A. Patil, Robin Jain and Prakhar Jain, “Identification of speakers from their hum,” P. Sojka et al. (Eds) TSD, Lecture Notes in Artificial Intelligence, LNAI, Springer-Verlag, Berlin Heidelberg, Germany, pp. 461-468, 2008.

[13] Hemant A. Patil and T. K. Basu, “A novel approach to language identification using modified polynomial networks,” B. Prasad and S.R.M. Prasanna (Eds.), Speech, Audio, Image and Biomedical Signal Processing using Neural Networks, Studies in Computational Intelligence, Springer-Verlag, Berlin Heidelberg, Germany, vol.83, pp. 117-144, March 2008.

[14] Hemant A. Patil, P. K. Dutta and T. K. Basu, “The wavelet packet based cepstral features for open set speaker classification in Marathi,” M. Spiliopoulou et al. (Eds) ‘Studies in Classification, Data Analysis, and Knowledge Organization’, Springer-Verlag, Berlin Heidelberg, Germany, pp. 134-141, 2006.

[15] Hemant A. Patil, P. K. Dutta and T. K. Basu, “Person authentication using voice biometrics,” J. Dittmann et al. (Eds.), New Advances in Multimedia Security, Biometrics, Watermarking and Cultural Aspects, pp. 119-134, Logos Verlag Berlin, Germany, 2006.

[16] Hemant A. Patil, P. K. Dutta and T. K. Basu, “On the mono-lingual and cross-lingual speaker identification for Indian and European languages,”        J. Dittmann et al.   (Eds.), New Advances in Multimedia Security, Biometrics, Watermarking and Cultural Aspects, pp. 213-220, Logos Verlag
      Berlin, Germany, 2006. 

[D] Conferences

        D.1) International                      

[17]  Hemant A. Patil and T. K. Basu, “Detection of bilingual twins by Teager energy based features,” in Int. Conf. on Signal Processing and Communications, SPCOM’04, IISc, Bangalore, pp. 32-36, Dec. 11-14, 2004 (IEEExplore).

[18]  Hemant A. Patil and T.  K. Basu, “Text-independent identification of identical twins for Marathi language in noisy environments,” in Proc. Int. Conf. on Artificial Intelligence in Engineering and Technology, ICAIET’04, Malaysia, pp. 190-196, Aug. 3-5, 2004.

[19]  Hemant A. Patil and T. K. Basu, “Designing speech corpus for twin identification experiments in Indian languages”, in Int. Conf. on Natural Language Processing, ICON’04, IIIT Hyderabad, Dec. 19-22, 2004.

[20]  Gagan Porwal, Hemant A. Patil and T. K. Basu, “Effect of GSM-FR coding standard on performance of text-independent speaker identification”, in Int. Conf. on Advanced Computing and Communications, ADCOM’04, Ahemdabad, Dec. 13-15, 2004.

[21]  Gagan Porwal, Hemant A. Patil and T. K. Basu, “Effect of speech coding on text-independent speaker identification”, in Int. Conf. on Intelligent Sensing and Information Processing, ICISIP’04, Chennai, pp. 415-420, Jan. 4-7, 2005 (IEEExplore).

[22]  Hemant A. Patil and T. K. Basu, “Identification of twins in multilingual environment using Teager energy operator,” in Int. Conf. on Speech and Language Technology, ICSLT’04, Noida, India, Nov. 17-19, 2004.

[23]  Hemant A. Patil and T. K. Basu, “Design of speech corpus for ASR in multilingual environment,” in Int. Workshop on Standardization of Speech Database, Oriental COCOSDA, India, Delhi, Nov. 17-19, 2004.

[24]  Hemant A. Patil and T. K. Basu, “Speech corpora for speaker classification experiments in Indian languages”, in Int. Conf. on Emerging Technology, ICET’04, KIIT Orissa, India, Allied Publishers, pp. 71-78, Dec. 22-24, 2004.

[25]  Hemant A. Patil and T. K. Basu, “Identification of twins in Hindi by Teager energy Mel cepstrum”, in Int. Conf. on Emerging Technology, ICET’04, KIIT Orissa, India, Allied Publishers, pp. 79-87, Dec. 22-24, 2004.

[26]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “The wavelet packet based cepstral features for open set speaker classification in Marathi,” Presented in 29th Annual Conference of the German Classification Society Otto-von-Guericke-University Magdeburg (GfKl 2005) "From Data and Information Analysis to Knowledge Engineering", pp. 199 (Abstract), March 9-11, 2005.

[27]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “Speaker classification using wavelet packet based features,” Presented in EU-India Culture Tech Workshop, IIT Kharagpur, Nov. 7-8, 2005.

[28]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “Effectiveness of LP based features for identification of professional mimics in Indian languages”, in Int. Workshop on Multimodal User Authentication, MMUA06, Toulouse, France, May 11-12, 2006.

[29]  Hemant A. Patil and T.K. Basu, “A new data fusion technique and performance measure for identification of twins in Marathi,” in Int. Symp. Chinese Spoken Lang. Proc., ISCSLP06, Singapore, Special Session on Speaker Recognition, Companion volume, Dec. 2006.

[30]  Hemant A. Patil, S. Ghosh, A. Si and T. K. Basu, “Design of cross-lingual and multilingual corpora for speaker recognition research and evaluation in Indian languages,” in Int. Symp. Chinese Spoken Lang. Proc., ISCSLP06, Singapore, Special Session on Multilingual Corpora Development, Companion volume, Dec. 2006.

[31]  Hemant A. Patil, Debee Prakash, Bikas Kar, Bishnu Bhatta, Biswajit Kar and T. K. Basu, “Corpora for speaker recognition research and evaluation in Oriya,” in  IEEE Int. Conf. on Industrial Tech., IEEE ICIT’06, Dec. 15-17, 2006, Mumbai, INDIA (IEEExplore).

[32]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “On the investigation of spectral resolution problem for identification of female speakers in Bengali , in  Special Session on Person Authentication: Voice and other biometrics, IEEE Int. Conf. on Industrial Tech., IEEE ICIT’06, Dec. 15-17, 2006, Mumbai, INDIA (IEEExplore) (regarded as excellent paper in this session by the esteemed reviewers) (IEEExplore) .

[33]  Hemant A. Patil and T.K. Basu, “Identifying phonetically similar languages using Teager energy based cepstrum,” in special session on “Frontiers of Language Processing and Information Retrieval for Asian Languages”, in Int. Conf. on Artificial Intelligence and Pattern Recognition, AIPR-07, Florida, USA, July 9-12, pp.1-8,  2007.

[34]  Hemant A. Patil and T. K. Basu, “Advances in speaker recognition: A feature based approach,” Int. Conf.  Artificial Intelligence and Pattern Recognition, AIPR, Orlando, Florida, USA, July 9-12, pp. 528-537, 2007 (Invited Paper).

[35]  Neeharika Buddha and Hemant A. Patil, “Corpora for analysis of infant cry,” in Int. Conf. on Speech Databases and Assessments, Oriental COCOSDA 2007, Hanoi, Vietnam, Dec. 4-6, 2007.

[36]  Nimish Singh and Hemant A. Patil, “Speech corpus for speaker recognition research and evaluation in Urdu,” in Int. Conf. on Speech Databases and Assessments, Oriental COCOSDA 2007, Hanoi, Vietnam, Dec. 4-6, 2007.

[37]  Hemant A. Patil and T. K. Basu, “Designing neural network using polynomial RBF for language identification” in Int. Conf. Neural Information Processing, ICONIP 2007, pp. 107, Japan (Abstract). 

[38]  Hemant A. Patil and T.K. Basu, “Designing quadratic spline wavelet for subband based speaker classification,” in Workshop on Image and Signal Processing, WISP-07 IIT Guwahati, Dec. 28-29, 2007.

[39]  Vikrant Tomar and Hemant A. Patil, “On the development of variable length Teager energy operator (VTEO),” in Interspeech 2008, Brisbane, Australia, 22-26 September, pp. 1056-1059, 2008.

[40]  Hemant A. Patil, Robin Jain and Prakhar Jain, "A novel approach to identification of speakers from their hum,” in 7th  Int. Conf. Advances in Pattern Recognition, ICAPR, ISI Kolkata, , IEEE Computer Society,  pp. 167-170, Feb. 4-6, 2009(IEEExplore).

[41]  Hemant A. Patil and T. K. Basu, “A novel modified polynomial networks design for dialect recognition,” 7th Int. Conf. Advances in Pattern Recognition, ICAPR, ISI Kolkata, IEEE Computer Society, pp. 175-178, Feb. 4-6, 2009(IEEExplore).

[42]  Hemant A. Patil, Sunayana Sitaram and Esha Sharma, “DA-IICT cross-lingual and multilingual corpora for speaker recognition,” 7th Int. Conf. Advances in Pattern Recognition, ICAPR, ISI Kolkata, IEEE Computer Society, pp. 187-190, Feb. 4-6, 2009(IEEExplore).

[43]  Hemant A. Patil, “Infant identification from their cry,” 7th Int. Conf. Advances in Pattern Recognition, ICAPR, ISI Kolkata, IEEE Computer Society, pp. 107-109, Feb. 4-6, 2009(IEEExplore).

[44]  Nirmalya Sen, Hemant A. Patil and T. K. Basu, “A new transform for robust text-independent speaker identification,”  in IEEE INDICON 2009, Ahmedabad, India.

[45]   Siddarth Rai Mahendra, Hemant A. Patil, Narendra Kumar Shukla, Pitch estimation of musical notes for Indian classical music,” in IEEE INDICON 2009, Ahmedabad, India.

[46]  Mayank Mishra and Hemant A. Patil, “Design and Implementation of HMM-VQ based isolated digit recognition system,” in Special Session on Speech, Audio, Image and Video Processing using AI, IICAI 2009, India.

[47]  Hemant A. Patil and Keshab K. Parhi, “Novel variable length Teager energy based features for person recognition from their hum,” accepted  in Proc. Int. Conf.  Acoust., Speech and Signal Proc., ICASSP 2010, Texas, Dallas, USA.

       D.2) National

[48]  Snehesh Mitra, Hemant A. Patil and T. K. Basu, “Polynomial classifier techniques for speaker identification in Indian languages,” in Proc. of National System Conference, NSC’03, IIT Kharagpur, India, pp. 304-308, Dec. 17-19, 2003.

[49]  Hemant A. Patil and T. K. Basu, “Text-independent identification of identical twins for Hindi language in noisy environments,” in Proc. of National Conf. on Emerging Techniques in Electrical Engineering, Etee’04, Chennai, India, Jan. 23-24, 2004.

[50]  Hemant A. Patil and T. K. Basu, “Comparison and evaluation of LP based features for text-independent identification for female speakers in Hindi language,” in Proc. of National Conf. on Emerging Techniques in Electrical Engineering, Etee’04, Chennai, India, Jan. 23-24, 2004.

[51]  Hemant A. Patil and T. K. Basu, “Comparison and evaluation of LP based features for text-independent identification for female speakers,” in Proc. of National Conf. on Control, Communication and Information Systems, CCIS’04,  Goa, India, pp. 41-46, Jan. 23-24, 2004.

[52]  Hemant A. Patil and T. K. Basu, “Comparison of subband cepstrum and Mel cepstrum for open set speaker classification”, in IEEE INDICON, IIT Kharagpur, pp. 35-40, Dec. 20-22, 2004 (IEEExplore).

[53]  Hemant A. Patil and T. K. Basu, “Teager energy Mel cepstrum for identification of twins in Marathi”, in IEEE INDICON, IIT Kharagpur, pp. 58-61, Dec. 20-22, 2004 (IEEExplore).

[54]  Hemant A. Patil, Tauseef Ahmad, Snehesh Mitra and T. K. Basu, “Comparison of performance of different speech features for text-independent speaker identification of female speakers in Urdu language,” in National System Conference, NSC’04, VIT, Vellore, India, pp. 254-258, Dec. 16-18, 2004.

[55]  Hemant A. Patil and T. K. Basu, “Speech corpus for text/language independent speaker recognition in Indian languages,” Addendum to the lecture compendium, in Proc. of National Symposium on Morphology, Phonology and Language Engineering, SIMPLE’04, IIT Kharagpur, pp. A1-A4, March 19-21, 2004.

[56]  Hemant A. Patil, Tauseef Ahmad and T. K. Basu, “LP based features for multilingual speaker identification of identical twins in Indian languages,” in Proc. of Conf. on Distributed Processing and Networking, DPN’04, IIT Kharagpur, pp. 221-227, June 11-13, 2004.

[57]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “Comparison of performance of different speech features for text-independent identification of professional mimic in Hindi and Urdu languages,” in National Symposium on Acoustics, NSA 2004, Mysore, India, Nov. 25-27, 2004.

[58]  Hemant A. Patil, P. K. Dutta and T. K. Basu, “The Teager energy Mel Cepstrum for speaker identification in multilingual environment,” in National Symposium on Acoustics, NSA 2004, Mysore, India, Nov. 25-27, 2004.

[59]  Hemant A. Patil, Arindam Kesh, D. Krishna Bhaskar, Kumara Ganesh, S. Barathi, S. Yamini, Shauryadipta Sarkar and T. K. Basu, “Comparison of different features for identification of females in multilingual environment,” in National Conference on Communications, NCC’05, IIT Kharagpur, India, pp. 300-304, Jan. 28-30, 2005.

[60]  Gagan Porwal, Hemant A. Patil and T. K. Basu, “Speech compression strategy for text-independent speaker identification,” in National Conference on Signal Processing, Communication and Control, SPCCN01 2005, Pune, India, pp. 140-145, July 1-3, 2005.


Teaching


Tutorials


Professional Membership 


Professional Services
A) Reviewer

    
  Journals


    Conferences

B) Associate Editor

c)  Program Commitee Member   

D) Organizing committee member

      
 E) Book Review

 F) Tutorial Speaker

Invited Talks  

Honorary Work