Siddharth Sehgal BSc, MSc (OR), MSc (ACS), PgDip (CS)

ScHARR
University of Sheffield
30 Regent Court
Regent Street
Sheffield S1 4DA

Tel: (+44) (0)114 222 2996
E-mail: s.sehgal@sheffield.ac.uk
Room: : 1.06, First Floor, The Innovation Centre

Biography

I received an undergraduate degree, BSc in Mathematics from the University of Delhi, India in 1996 and a postgraduate degree, MSc in Operational Research from the University of Delhi, India in 1999. I also have a computational background with a 3 year professional diploma in Network Centered Computing (2000) and a Post Graduate Diploma (PgDip) in Computer Science.

From 2000 – 2003 I have worked as a Software Engineer at SBICPSL which is a joint venture between India's largest bank, State Bank of India (SBI) and the financial service unit of General Electrics (GE Capital).

I pursued another postgraduate degree, MSc in Advanced Computer Science from the University of Sheffield between 2003 – 2004 and since 2005 I have worked as a Research Associate at the Department of Computer Science and Human Communication Sciences. I am currently working at the School of Health and Related Research (ScHARR) department. I am involved in the Research and Development of embedded speech technology in clinical domains such as assistive technology and environmental control systems. I work closely with the Speech and Hearing (SpandH) group in the Department of Computer Science and two multi-disciplinary research groups, viz. Clinical Applications of Speech Technology (CAST) and Rehabilitation and Assistive Technology (RAT), which focuses on providing latest research and user-friendly technologies to enable independent living and improved healthcare for older and disabled people.

Since 2010, I am also pursuing a part-time PhD from the Department of Human Communication Sciences at the University of Sheffield.

Research Interests

• Automatic speech recognition & adaptation of dysarthric speech
• Machine Learning
• Software Engineering & embedded software development.
• Applying embedded speech technology in clinical domains such as assistive technology, environmental control systems and speech & language therapy.
• Algorithm Design

Associated Projects

Voice Input Voice Output Communication Aid (VIVOCA)
Speech Driven Environmental Control System (SPECS)
• Supervised Care and Rehabilitation Involving Personal Tele-Robotics (SCRIPT)
Self Management and Rehabilitation Technologies (SMART-3)

PhD Project

My PhD thesis focuses on finding optimal strategies for robust speaker independent and pronunciation modelling of dysartrhic speech.

Supervisors

Dr. Stuart Cunningham, Department of Human Communication Science, University of Sheffield.
Prof. Roger Moore, Department of Computer Science, University of Sheffield.

Publications

• Gemmeke, J. F, Sehgal, S., Cunningham, S., Hamme, H. V. (2014), “Dysarthric Vocal Interfaces with Minimal Training Data”. In: IEEE Spoken Language Technology Workshop.
• Hawley, M., Cunningham, S., Green, P. Enderby, P. Palmer, R. Sehgal, S. O'Neill, P. (2013). “A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment”. In: Neural Systems and Rehabilitation Engineering, IEEE Transactions on PP.99, p. 1.
• Hawley, M., Cunningham, S., Cardinaux, F., Coy, A., O'Neill, P., Seghal, S. and Enderby, P. (2007). “Challenges in developing a voice input voice output communication aid for people with severe dysarthria”. In: AAATE 2007 : 9th European Conference for the Advancement of Assistive Technology in Europe, Oct 2007, San Sebastian, Spain.
• Lu, Y., Lu, F., Sehgal, S., Gupta, S.,Du, J., Tham, C.H., Green, P., Wan, V.. “Multitask Learning in Connectionist Speech Recognition”, Tenth Australian International Conference on Speech Science & Technology, Macquarie University, Sydney, Australia, 2004.
• Attended and presented a poster at “Google's 1st doctoral workshop on speech technology”, Google, London, April 2014.
• A talk at a workshop on “Innovations and Applications in Speech Technology” in March 2012 in Ireland at the University College Dublin for the SPECS project “Speech Driven Environmental Control System”• Hawley, M., Cunningham, S., Green, P. Enderby, P. Palmer, R. Sehgal, S. O'Neill, P. (2013). “A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment”. In: Neural Systems and Rehabilitation Engineering, IEEE Transactions on PP.99, p. 1.
• Hawley, M., Cunningham, S., Cardinaux, F., Coy, A., O'Neill, P., Seghal, S. and Enderby, P. (2007). “Challenges in developing a voice input voice output communication aid for people with severe dysarthria”. In: AAATE 2007 : 9th European Conference for the Advancement of Assistive Technology in Europe, Oct 2007, San Sebastian, Spain.
• Lu, Y., Lu, F., Sehgal, S., Gupta, S.,Du, J., Tham, C.H., Green, P., Wan, V.. “Multitask Learning in Connectionist Speech Recognition”, Tenth Australian International Conference on Speech Science & Technology, Macquarie University, Sydney, Australia, 2004.
• A talk at a workshop on “Innovations and Applications in Speech Technology” in March 2012 in Ireland at the University College Dublin for the SPECS project “Speech Driven Environmental Control System”.