SSN TDSC

The SSNCE Database of Tamil Dysarthric Speech.

SSN-TDSC is a corpus of Tamil dysarthric speech, collected by Speech Lab for rehabilitation and assistive-technology research, and catalogued with the Linguistic Data Consortium (LDC).

View on LDC Download license request form

Access

Access to SSN-TDSC is restricted to academic and scientific research, including the creation and training of machine learning models, and is granted only under a signed license agreement with the Center for Speech Technology, Dept. of ECE, SSN College of Engineering.

Download the SSN-TDSC License Request & Agreement Form above.
Complete and sign the form, naming the recipient scientist and intended research use.
Email the signed form to vijayalakshmip@ssn.edu.in.

Email the completed form

Required Citation

All publications, presentations, and derivative works using SSN-TDSC must cite the following:

Mariya Celin T A, Nagarajan T and Vijayalakshmi P, "Dysarthric speech corpus in Tamil for rehabilitation research," 2016 IEEE Region 10 Conference (TENCON), Singapore, 2016, pp. 2610–2613. DOI: 10.1109/TENCON.2016.7848510.
T. A. Mariya Celin, G. Anushiya Rachel, T. Nagarajan, and P. Vijayalakshmi, "A Weighted Speaker-Specific Confusion Transducer-Based Augmentative and Alternative Speech Communication Aid for Dysarthric Speakers," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 2, pp. 187–197, Feb. 2019. DOI: 10.1109/TNSRE.2018.2887089.