Rohit Kumar =========== Research Engineer, Speech Technology Group, Language Technologies Research Center, IIIT Hyderabad ====================================================================== CAREER OBJECTIVE ================ To pursue and collaborate in research, development and teaching of technologies at academic / research oriented institutes and organizations and to work towards innovation of products for mass use ====================================================================== EDUCATIONAL OBJECTIVE ===================== To join and pursue a Ph. D. program specializing in Speech Technology and Spoken Language Systems in an internationally reckoned group with significant contributions to this field ====================================================================== PERSONAL PARTICULARS ==================== Male, Born on 09 January 1982 Place of Birth: Hyderabad, INDIA Citizenship: INDIAN Natural Languages Known: English, Hindi, Telugu Postal Address: LTRC, IIIT Hyderabad, Gachibowli, Hyderabad, INDIA 500 019 Telephone: +91 – 040 – 23001967 Ext: 174 Email: rohit@iiit.net, rohitofpec@computer.org Web Address: http://nlp.iiit.net/~rohit/ ====================================================================== EDUCATIONAL BACKGROUND ====================== Bachelor of Engineering (in Computer Science): August 1999 – May 2003 Percentage: 71.36% (7136 / 10000) (1st Division with Honours) College: Punjab Engineering College, Chandigarh University: Panjab University, Chandigarh, INDIA Intermediate (Junior College): June 1997 – May 1999 Percentage: 84% (1st Division) School: D A V Senior Secondary School, Chandigarh Matriculation: May 1996 – April 1997 Percentage: 66% (1st Division) School: Shishu Niketan Senior Secondary School, Chandigarh ====================================================================== SOME OF THE SEVERAL COURSES TAKEN ================================= .Soft Computing .Multimedia Design and Applications .Artificial Intelligence .Digital Signal Processing .Digital Electronics and Wave - shaping .Analysis and Design of Algorithms .Operating System Concepts .Computer and Communication Networks .Software Engineering .Discrete Structures .Computer Graphics .Computer Arch. & Organization .Coordinator for an introductory course on Speech Technology at IIIT Hyderabad, Fall 2003 .Coordinator for Designing Speech Systems course at IIIT Hyderabad, Spring 2004 ====================================================================== WORK / RESEARCH EXPERIENCE ========================== July 2003 - Presently: Research Engineer in Speech Technology Group of Language Technologies Research Center (LTRC), International Institute of Information Technology (IIIT), Hyderabad, INDIA. Involved in development and improvement of Text – to – Speech Systems and related Applications for Indian Languages December 2002 – January 2003: Winter Internship at LTRC, IIIT Hyderabad. Contributed to development of Unrestricted Domain Text to Speech Systems for Indian Languages and Low Memory Device Synthesizer June 2002 – July 2002: Summer Internship at LTRC, IIIT Hyderabad in Summer 2002. Contributed to development of Unrestricted Domain and Limited Domain Text – to – Speech systems and developed speech output applications for Simputer ====================================================================== AREAS OF INTEREST ================= .Speech Technologies .Spoken Language Systems .Natural Man/Machine Interfaces .Natural Language Processing .Artificial Intelligence .Computer Graphics ====================================================================== COMPUTING SKILLS AND EXPOSURE ============================= Languages: C / C++ / VC++, 8085 / 8086 (Assembly), QuickBASIC, LISP, PERL, HTML Operating Systems: Linux, Windows NT/9X, DOS (core), SCO Unix, Solaris Hardware Platforms: PCs, Sun E-450 Servers, Simputer (Strong ARM) Toolkits/ Libraries: Qt, GTK+, STL, Sockets, Festvox Framework .Sound knowledge of Data Structure, Algorithms, OOP Design Patterns .Practical Exposure of administering networks at school, college and hostel ====================================================================== RESEARCH PROJECTS UNDERTAKEN ( IN DATE WISE ORDER ) ============================ Photorealistic Visual Speech Synthesis ====================================== Independent Research Location: LTRC, IIIT Hyderabad Duration: October 2003 – Presently .Study of Viseme shapes, Phoneme to Viseme Mappings for Target Languages .Issues of modeling Co – articulation: Experimenting with a diviseme based approach for this .Developed Greedy Approach for Automated Optimal Text Selection by to provide full coverage of divisemes in a minimal representative corpus GASpSynthesizer =============== Independent Research Location: LTRC, IIIT Hyderabad Duration: August – September 2003 (paper work pending) .Developed and Experimenting with a Genetic Algorithm based approach for Unit Selection in the framework of Concatenative Speech Synthesis .Choice of Appropriate Fitness Functions; Size of Initial Population; Implementation of Selection, Combination, Elitism and Mutation operators are some of several issues that need to be experimented with Unit Pruning in Speech Database without loss of Naturalness =========================================================== Independent Research Location: LTRC, IIIT Hyderabad Duration: August – September 2003 (paper work pending) .Developed an approach to prune away units which do not contribute to prosodic coverage of the units or the prosodic coverage provided by which is rarely required (statistically) .Experiments to find the optimum extent of pruning without significant loss of naturalness are underway PECMail: Email Client for Hindi (with Speech Support) - Application Development Project ===================================================== Project Guide: Mr. Sanjeev Sofat Location: Punjab Engineering College, Chandigarh Duration: 8th Semester, January – May 2003 .A basic Email Client with Support for sending and receiving mails in Hindi besides English .Common features of Email clients like POP3 access and SMTP implementation, compose, reply, forward, etc. where implemented .Incoming mails in Hindi are read out by the client .A GUI based keyboard for typing Hindi for users unaware of Hindi Keyboard Layout Rule – based Approach for Building Non – Native Pronunciation Lexicon using a Native Lexicon =========================================================================================== Independent Research Location: Punjab Engineering College, Chandigarh Duration: February – May 2003 .Correspondence between Native and Non Native Pronunciations of English observed and rule format for modeling the differences has been proposed .Generic Algorithm for mapping Graphemes to Phonemes in a word’s pronunciation developed. .Experimented with Example based Approach for automatically building rules Low Memory Device Synthesizer ============================= Project Guide: Mr. S. P. Kishore Location: LTRC, IIIT Hyderabad Duration: December 2002 – January 2003 .Contributed to development of a Low Memory Device Synthesizer (LMDS) for Simputer enabling speech synthesis for Indian Languages (currently Hindi and Telugu) .Automated methods for selecting the best units from a given speech database were conceived and experimented with .Good Quality Speech Synthesis is achieved for Database Size as small as 1.4 MB Samachaar Vaani: News Reader - Application Development Project ============================ Project Guide: Mr. Sanjeev Sofat Location: Punjab Engineering College, Chandigarh Duration: 7th Semester, August – December 2002 .Developed a News Reader Software that reads out latest news from BBC Hindi News Websites .A flexible Server / Reader Framework was proposed that would enable any news service provider to provide spoken news service using Automatic Speech Synthesis hence avoiding lot of manual costs involved in providing spoken news service Indian Language Speech Synthesizer based on Data Driven Approach ================================================================ Project Guide: Mr. S. P. Kishore Location: LTRC, IIIT Hyderabad Duration: June – July 2002 .Contributed to development of a Generic Unrestricted Domain Synthesizer for Indian Languages using Syllable level Unit Selection & Concatenation on lines of the Limited Domain Synthesizer .Used a Prosodic Mismatch Function to select the most natural (prosodically harmonious) sequence of units in given phonetic contexts .Several Text Processing Issues related to Indian Languages like Syllablification and Inherent Vowel Suppression were discussed and implemented Continued System Development (August 2003 onwards) .More recently, a robust API for the Indian Language TTS has been implemented to facilitate application development using the system in Windows .Development of font converters and text processing modules among various Hindi & Telugu Fonts, Unicode, ISCII and other notations Limited Domain Speech Synthesizer Synthesizer ============================================= Project Guide: Mr. S. P. Kishore Location: LTRC, IIIT Hyderabad Duration: June – July 2002 .Contributed to development of a Generic Limited Domain Synthesizer for Indian Languages based on Syllable level Unit Selection Related Applications ==================== .Talking Tourist Aid Adapted a Talking Tourist Aid Application for Hindi and Telugu to use the Limited Domain speech synthesizers and ported it to Simputer .Talking Clock Adapted a Talking Clock Application for Hindi and Telugu to use the Limited Domain speech synthesizers and ported it to Simputer Deepti: Computing Time Companion ================================ Project Guide: Mr. Sanjeev Sofat Location: Punjab Engineering College, Chandigarh Duration: 6th Semester, February – May 2002 .Developed an Intelligent Hindi Speaking bot with speech out capability using diphone databases .Used AIML Engine for providing Natural Language Dialog capabilities to the bot .Please see: http://deepti.nourl.org/ .The Project was featured on BBC Technology Review Show “Go Digital” and in several other national publications Speaker Verification: Speech based biometric Authentication =========================================================== .Implemented a speaker verification algorithm based on rate of positive zero crossing for use in project on telephonic authentication of speaker as the software component of major project of one of my seniors Several other projects were undertaken as a part of practical work of various courses. For a exhaustive list of these please see http://www.geocities.com/rohitofpec/projects.htm ====================================================================== PUBLICATIONS ============ ( Downloads are available at http://nlp.iiit.net/~rohit/publications.htm ) Conferences: ============ "Building Non - Native Pronunciation Lexicon for English using a Rule based Approach" Rohit Kumar, Amit Kataria, Sanjeev Sofat Presented at International Conference on Natural Language Processing (ICON) 2003, December 2002, Mysore, INDIA Earlier Accepted at: IEEE International Conference on Information Reuse and Integration (IRI), 2003 October 2003, Las Vegas, Nevada, USA < could not be presented due to financial constraints > “Implementing a Natural Language Conversational Interface for Indian Language Computing” Rahul Jindal, Rohit Kumar, Ritvik Sahajpal, Sanjeev Sofat, Shailendra Singh Presented at Sixth International Conference on Information Technology (CIT), 2003 December 2003, Bhubaneswar, INDIA “Samachaar Vaani: A Framework for providing Automated Spoken News Service” Rohit Kumar, Anuj Singla, Sanjeev Sofat Sixth International Conference on Information Technology (CIT), 2003 December 2003, Bhubaneswar, INDIA “Experiments with Unit Selection Speech Databases for Indian Languages” S. P. Kishore, Alan W. Black, Rohit Kumar, Rajeev Sangal Presented at National Seminar on Language Technology Tools: Implementation of Telugu October 2003, Hyderabad, INDIA “A Data-Driven Synthesis Approach for Indian Languages using Syllable as Basic Unit” S. P. Kishore, Rohit Kumar, Rajeev Sangal Presented at International Conference on Natural Language Processing (ICON) 2002, December 2002, Mumbai, INDIA Technical Contributions to Student Publications and Contests in College: ================================================================ “A Framework for E – Governance in India with Local Language Support” in student paper contest organized during National Productivity Week by National Productivity Council, February 2003 “Observing and being a part of Evolution of Language: Some Random Thoughts” for IEEE Computer Society Student Chapter Bi Annual Publication POTENTIAL, vol. II, 2003 “Data Driven Approaches: A Basis for Everything” for P. E. C. Student Magazine: PECMag 2003 ====================================================================== PROFESSIONAL MEMBERSHIPS AND ACTIVITIES ======================================= I E E E Computer Society .Founder Secretary of IEEE Computer Society Student Branch Chapter at my college for the 2002 – 03 .Have played the key role in establishing and building up the student branch chapter through its initial years .Student Member since July 2001. I E E E .Student Member of IEEE since July 2001 .Was actively involved in activities of Student Branch at my college and volunteered in organizing industry institute interactions and student paper contests. .Member of The Indian Science Congress Association ( I S C A ) for the year 2003 ====================================================================== AWARDS AND ACHIEVEMENTS ======================== IEEE Computer Society Richard E. Merwin Student Scholarship 2003 ================================================================ .Every year upto four students world over are selected to be recognized and rewarded for active leadership in IEEE Student branch chapters .Please see http://www.computer.org/students/schlrshp.htm#merwin for details about the scholarship and selection criteria Silver Medal for Best Final Semester Project ============================================ The silver medal for Best Final Semester Project in Department of Computer Science and Engineering will is to be awarded to me during Annual Convocation Student Programming Contests ============================ .1st prize in Pre-defined software contest in PECFest 2001 (PEC technical festival 2001) .1st prize in On-the-spot software contest in PECFest 2001 .2nd prize in Debugging contest in PECFest 2001 .1st prize in Pre-defined software contest in Panoplia (PEC technical festival 2000) State Science Exhibitions ========================= .3rd prize in State Science Exhibition organized by State Institute of Education, UT, Chandigarh, in 1998 for projects on Traffic control by computers .1st prize in State Science Exhibition organized by State Institute of Education, UT, Chandigarh, in 1997 for projects on Role of IT in Education Technology EXTRA – CURRICULAR ACTIVITIES ============================= College’s Student Council ========================= .Co – opted member of College’s Student Council 2002 – 03 for excellence in technical activities .The Principal nominates upto four co – opted members for excellence in various circles Web Administrator for college website during 2002 – 03 ====================================================== My responsibilities included the aspect of uploading, maintenance and administration of the website Graphics Editor of PEC Editorial - Board for year 2002 – 03 =========================================================== PECMag, Souvenir and VISTA cover pages for the year 2002 – 03 were designed by me Headed Technical Committee of SemantiCa, December 2001 ====================================================== SemantiCa, an Intra College On-the-Spot programming contest is now the premier event organized annually by IEEE Computer Society Student Branch Chapter at PEC. It was conceived and implemented for the first time by me Co – Convener of Simulated Engineering and Medical Entrance Examination Event during 2001 ============================================================ Due to my contribution to the activity over years, I was appointed co – convenor of the event during 2001. It provided me with first hand experience in event management and organizing human and material resources Coordinator of National Service Scheme ( N S S ) PEC Unit during 2000 – 2001 ========================================================= OTHER INTERESTS =============== Cycling, Music, Movies, Badminton, Hiking ====================================================================== REFERENCES ========== Prof. Rajeev Sangal Director, International Institute of Information Technology, Hyderabad Gachibowli, Hyderabad, INDIA 500 019 E-mail: sangal [AT] iiit [DOT] net Mr. Sanjeev Sofat Head, Department of Computer Science & Engineering, Punjab Engineering College, Sector 12, Chandigarh, INDIA 160 012 E-mail: chestasofat [AT] yahoo [DOT] com Dr. Vasudeva Varma Assistant Professor, IIIT Hyderabad Presently supervisor of my work at LTRC, IIIT Hyderabad E-mail: vv [AT] iiit [DOT] net ======================================================================