Venkata Ramana Rao Gadde


Speech Technology and Research Lab

SRI International

333 Ravenswood Ave.

Menlo Park, CA 94025-3493

E-mail: (work) ramana@speech.sri.com

Telephone: 650-859-5653


RESEARCH INTERESTS


Speech Recognition, Speaker modeling, Natural Language Processing, Information Retrieval.


EXPERIENCE


Speech Technology and Research Lab, SRI International

Senior Research Engineer (2002 to present), Research Engineer (1998 to 2002), International Fellow (1996 to 1997).


Research on new Acoustic and Prosodic models for Speech Recognition and Speaker Identification.

Led the SRI team on SPINE evaluations winning the 2002 evaluation.


Dept. of Computer Science and Engineering, Indian Institute of Technology Madras, India

Lecturer (1988 to 1996), Assistant Professor (1996)


Research on Word Boundary Detection in Indian languages.

Teaching undergraduate and graduate CS students.


VOIS Project, Dept. of Computer Science and Engineering, Indian Institute of Technology Madras, India

Senior Project Officer-II (1986 to 1998)


Development of the Lexical Analysis module in the VOIS Speech Recognition system.


Electronics Corporation of India Ltd., Hyderabad, India

Technical Officer (1982 to 1984)


Installation and maintenance of Data Acquisition Systems. Managed a team of 2 technicians and 6 workers.


EDUCATION


Ph.D., Indian Institute of Technology, Madras, 1994, Major: Computer Science


M.Tech., Indian Institute Of Technology, Madras, 1986, Major: Computer Science


B.Tech., Indian Institute of Technology, Kharagpur,1982, Major: Electronics & Electrical Communication, Silver medalist


PUBLICATIONS


Journals and Reviewed Conferences


  1. The Modified Group Delay Function and its Application to Phoneme Recognition, Hema A Murthy and Venkata Gadde, Proc. 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing 2003 (ICASSP 2003), Vol. I, pp. 68-71.

  2. Prosodic knowledge sources for automatic speech recognition, D. Vergyri, A. Stolcke, V. R. R. Gadde, L. Ferrer, and E. Shriberg, Proc. 2003 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2003), Vol. I, pp. 208-211.

  3. Modeling duration patterns for speaker recognition, L. Ferrer, H. Bratt, V. R. R. Gadde, S. Kajarekar, E. Shriberg, K. Sonmez, A. Stolcke, and A. Venkataraman. Proc. European Conference on Speech Communication and Technology (Eurospeech 2003), pp. 2017-2020 .

  4. Building an ASR System for Noisy Environments: SRI's 2001 SPINE Evaluation System, Venkata Ramana Rao Gadde, Andreas Stolcke, Dimitra Vergyri, Jing Zheng, Kemal Sonmez and Anand Venkataraman, Proc. International Conference on Spoken Language Processing 2002(ICSLP 2002), pp. 1577-1580.

  5. Improved Modeling and Efficiency for Automatic Transcription of Broadcast News, Ananth Sankar, Venkata Ramana Rao Gadde, Andreas Stolcke and Fuliang Weng, Speech Communication(Special Issue on Broadcast News Transcription), Vol.37, Issue 1-2, pp133-158, May 2002.

  6. The SRI EduSpeak(TM) System: Recognition and Pronunciation Scoring for Language Learning, H. Franco, V. Abrash, K. Precoda, H. Bratt, R. Rao, and J. Butzberger, Proceedings of InSTIL 2000 (Integrating Speech Technology in Language Learning 2000), Dundee, Scotland.

  7. Modeling Word Duration, Venkata Ramana Rao Gadde, Proc. 6th International Conference on Spoken Language Processing(ICSLP 2000), Vol.1, pp601-604.

  8. Modeling Word Duration for Better Speech Recognition, Venkata Ramana Rao Gadde, Proc. Speech Transcription Workshop, University of Maryland, MD, May 16-19, 2000.

  9. The SRI March 2000 Hub-5 Conversational Speech Recognition System, Proc. Speech Transcription Workshop, University of Maryland, MD, May 16-19, 2000.

  10. Prosody Modeling for Speech Recognition and Understanding, Ramana Rao Gadde, Elizabeth Shriberg, Andreas Stolcke, Dilek Hakkani-Tur and Gokhan Tur, Proc. Hub-5 Conversational Speech Understanding Workshop, Baltimore, 1999.

  11. Parameter tying and Gaussian clustering for Faster, Smaller and Better Speech Recognition, Ananth Sankar and Ramana Rao Gadde, Proc. EUROSPEECH 99, vol.4, pp1711-1714.

  12. SRI's 1998 Broadcast News System - Towards Faster, Smaller, and Better Speech Recognition, Ananth Sankar, Ramana Rao Gadde and Fuliang Weng, Proc. DARPA Broadcast News Workshop 1999, pp281-286.

  13. Development of SRI's 1997 Broadcast News Transcription System, Ananth Sankar, Fuliang Weng, Ze'ev Rivlin and Ramana Rao Gadde, Proc. DARPA Broadcast News Transcription & Understanding Workshop 1998, pp91-96.

  14. Word Boundary Detection in Indian Languages from Pitch Variations, G.V.Ramana Rao and J.Srichand, Journal of the Acoustical Society of India, vol.XXIII, no.1, pp61-66, 1996.

  15. Word Boundary Detection using Pitch Variations, G.V.Ramana Rao and J.Srichand, International Conference on Spoken Language Processing(ICSLP'96), Philadelphia, pp813-816, Oct 1996.

  16. Graphical Representation of Speech Sounds, Nitin Adke and G.V.Ramana Rao, International Conference on Educational Computing (EDUCOMP '96), TTTI, Chandigarh, India, pp298-302, March 1996.

  17. A Computer aided Teaching Package for Microprocessor System Education, G.Peddareddappa, B.Veeraiah and G.V.Ramana Rao, International Conference on Educational Computing (EDUCOMP '96), TTTI, Chandigarh, India, pp282-288, March 1996.

  18. Detection of Word Boundaries in Continuous Speech using Pitch and Duration, G.V.Ramana Rao, Fourth Australian international conference on Speech Science and Technology (SST-92), Brisbane, Australia, pp789-793, Oct 1992.

  19. Detection of Word Final Vowels in Speech using First Formant Energy, G.V.Ramana Rao, Regional workshop on Computer Processing of Asian Languages (CPAL-2), Kanpur, pp243-247, March 1992.

  20. Word Boundary Hypothesisation in Hindi Speech, G.V.Ramana Rao and B.Yegnanarayana, Computer Speech and Language, vol.5, no.4, pp379-392, Dec 1991.

  21. Development of a Speech-to-Text system for Indian Languages, C.Chandra Sekhar, G.V.Ramana Rao, P.Eswar etal., Frontiers in Knowledge based Computing (KBCS 90), Pune, pp.457-466, Dec 1990.

  22. Word Boundary Hypothesisation in Hindi Speech, G.V.Ramana Rao, M.Prakash and B.Yegnanarayana, EUROSPEECH'89, Paris, vol.1, pp360-363, Sep 1989.

  23. Parsing Spoken Utterances in an Inflectional Language, M.Prakash, G.V.Ramana Rao, C.Chandra Sekhar and B.Yegnanarayana, EUROSPEECH'89, Paris, vol.1, pp546-549, Sep 1989.

  24. A Continuous Speech Recognition System for Indian Languages, B.Yegnanarayana, C.Chandra Sekhar, G.V.Ramana Rao, P.Eswar and M.Prakash, Regional workshop on Computer of Asian Languages (CPAL-1), Bangkok, pp347-356, Sep 1989.

RESEARCH GUIDANCE


Word Boundary Detection in Indian Speech and Its Application to Keyword Spotting, J.Srichand, M.S. Thesis, IIT Madras, 1996. (Jointly with Dr. Hema A. Murthy).


PRESENTATIONS (on web)


SRI 2001 SPINE Evaluation System, http://elazar.itd.nrl.navy.mil/spine/sri2/presentation/sri2001.html


SRI 2000 SPINE Evaluation System, http://elazar.itd.nrl.navy.mil/spine/spine1/sri/index.html