Sunil Sivadas

Senior Researcher
Tampere, Finland

In our daily life, interaction with digital world has become as essential as interaction with other humans. The interaction with digital world has moved from desktop to mobile and pervasive environments as we use technology to live our life efficiently and enjoyably. We interact with our friends, colleagues, family members and environment using context-dependent digital communication channels, possibly using multiple user interfaces. This has blurred the boundary between physical and digital worlds and challenges the traditional user interfaces based on WIMP (Window-Icon-Menu-Pointing device) paradigm. My research focuses on enabling intelligent multimodal interfaces that learn the needs of the user in various contexts.

Research Interests

• Signal processing and machine learning for analysis and classification of speech, audio and psychophysiological signals.
• Context modeling, sensing-based interaction and data mining.

Other Information

Education

•    Ph.D. , Electrical Engineering (2004),
Oregon Graduate Institute, Portland, Oregon, USA.

•    M.Tech., Electronic Design (1998),
Indian Institute of Science, Bangalore, India.

•    B.Tech., Electronics & Communication Engineering (1994),
University of Calicut, India.

Publications

Imre Kiss, Jussi Leppanen & Sunil Sivadas, "Nokia's System for TC-STAR EPPS English ASR Evaluation Task", in Proc. of TC-STAR Speech-to-Speech Translation Workshop, Barcelona, Spain , 2006.

Evgeny Karpov, Imre Kiss, Jussi Leppänen, Jesper Olsen, Daniela Oria, Sunil Sivadas and Jilei Tian, “Short Message Dictaton on Symbian Series 60 Mobile Phones” , in Proc. of ACM 8th International Conference on Human Computer Interaction with Mobile Devices and Services, Workshop on Speech in Mobile and Pervasive Environments (SiMPE), Espoo, Finland, 2006.

Evgeny Karpov, Imre Kiss, Jussi Leppänen, Jesper Olsen, Daniela Oria, Sunil Sivadas and Jilei Tian, “Short Message Dictaton on Symbian Series 60 Mobile Phones” , in Proc. of Eighth International Conference on Multimodal Interfaces (ICMI), Banff, Canada, 2006.

Morgan, N. Qifeng Zhu Stolcke, A. Sonmez, K. Sivadas, S. Shinozaki, T. Ostendorf, M. Jain, P. Hermansky, H. Ellis, D. Doddington, G. Chen, B. Cretin, O. Bourlard, H. Athineos, M., "Pushing the envelope - aside [speech recognition]", in IEEE Signal Processing Magazine, September 2005.

Misra, H. Ikbal, S. Sivadas, S. Bourlard, H. , “Multi-resolution Spectral Entropy Feature for Robust ASR”, in Proc. of ICASSP 2005, Philadelphia, USA.

Shajith Ikbal, Hemant Misra, Sunil Sivadas, Hynek Hermansky, Hervé Bourlard , “Entropy based Combination of Tandem Representations for Noise Robust ASR “, in Proc. of Interspeech 2004, Jeju Island, Korea.

S.Sivadas, H. Hermansky, "On Use of Task Independent Training Data in Tandem Feature Extraction", in Proc. of ICASSP 2004, Montreal.

B. Chen, S. Chang and S. Sivadas, "Learning Discriminative Temporal Patterns in Speech: Development of Novel TRAPS-Like Classifiers", in Proc. of Eurospeech 2003, Geneva.

S. Sivadas and H. Hermansky, "In Search of Target Class Definition in Tandem Feature Extraction", in Proc. of Eurospeech 2003, Geneva.

S. Sivadas and H. Hermansky, "Generalized Tandem Feature Extraction", in Proc. of ICASSP 2003, HongKong.

A. Adami and L. Burget and S. Dupont and H. Garudadri and F. Grezl and H. Hermansky and P. Jain, S. Kajarekar and N. Morgan and S. Sivadas, “QUALCOMM-ICSI-OGI Features for ASR", in Proc. of ICSLP 2002, Denver, Colorado, USA, Sep, 2002.

S. Sivadas and H. Hermansky, "Hierarchical Tandem Feature Extraction", in Proc. of ICASSP 2002, Orlando, Florida, USA.

D. Ellis, R. Singh, S. Sivadas, "Tandem Acoustic Modeling In Large-Vocabulary Recognition", in Proc. of ICASSP 2001, Salt Lake City, USA.

C. Benitez, L. Burget, B. Chen, S. Dupont, H. Garudadri, H. Hermansky, P. Jain, S. Kajarekar, N. Morgan and S. Sivadas, "Robust ASR front-end using spectral-based and discriminant features: experiments on the Aurora tasks ", in Proc. of Eurospeech 2001, Aalborg, Denmark, September 2001.

S. Sivadas, P. Jain, H. Hermansky, "Discriminative MLPs In HMM-Based Recognition Of Speech in Cellular Telephony", in Proc. of ICSLP 2000, Beijing, China.

Sunil Sivadas, Supriyo Palit, Sreenivas T.V., “HMM based fast keyword spotting algorithm with no garbage models”, in Proc. of ICSP 1997, Singapore.

Patents

1 Granted and 6 pending applications in the areas of context modeling, signal representation, multimedia systems and speech recognition algorithms.