About us


      We are working under a project sponsored by the Department of Electronics and Information Technology (DEIT), Govt of India for developing Assamese and Manipuri Text-to-speech synthesis system. It involves building systems for synthesizing natural speech in native Assamese and Manipuri tone from a given text and building user friendly GUIs for the common people.



People


Faculty

Prof. S. R. Mahadeva Prasanna
Dr. Sanasam Ranbir Singh

Project Scholar

Nagaraj Adiga
Bidisha Sharma
Loitongbam Gyanendro Singh
Rajlakshmi Saikia

Former Project Scholar

Konjengbam Anand
Nishma Laitonjam
Lenin Laitonjam
Karishma Saikia
Meenakshi Das
Hidam Sanatomba Meitei
Indrajit Kalita
Hridoy Shankar Dutta
Nanaobi Huidrom
Mayanglambam Bidyalakshmi Devi




Publication

  1. N. Adiga and S. R. M. Prasanna, “Significance of instants of significant excitation for source modeling,” in INTERSPEECH-2013, Lyon, France, 2013.
  2. N. Adiga and S. R.M. Prasanna, “Epochs Based Compression of LP Residual for Source Modeling in Text-to-Speech Synthesis”, in proc NCC, IIT Kanpur, India , 2014.
  3. N. Adiga and S. R. M. Prasanna, “Significance of Epoch Identification Accuracy for Prosody Modification”, in SPCOM 2014, IISC Bangalore, India , 2014.
  4. N. Adiga and S. R. M. Prasanna, “A Hybrid Text-to-Speech Synthesis using Vowel and Non Vowel like regions”, in proc INDICON, Pune, India , 2014.
  5. Bidisha Sharma and S. R. M. Prasanna, “Faster Prosody Modification using Time Scaling of Epochs”, in proc INDICON, Pune, India , 2014.
  6. Nagaraj Adiga and S. R. M. Prasanna, "Detection of Glottal Activity Using Different Attributes of Source Information," in IEEE Signal Processing Letters, vol. 22, no. 11, pp. 2107-2111, Nov. 2015.
  7. Bidisha Sharma, Nagaraj Adiga and S R M Prasanna, “Development of Assamese Text-to-speech synthesis system,” in TENCON, Macau, China, November 2015.
  8. Bidisha Sharma and S R M Prasanna, “Improvement of Syllable based TTS System in Assamese using Prosody Modification,” 2015 Annual IEEE in India Conference (INDICON), Delhi, Dec 2015
  9. Nagaraj Adiga and S R M Prasanna, “Source Modelling for HMM based speech synthesis using integrated LP residual,” ICASSP, March 2016.
  10. Bidisha Sharma and S R M Prasanna, “Polyglot Speech Synthesis: A Review ,” doi:10.1080/02564602.2016.1192963, IETE Technical Review, 2016
  11. Bidisha Sharma and S R M Prasanna, “Speech Synthesis in Noisy Environment by Enhancing Strength of Excitation and Formant Prominence,” INTERSPEECH, 2016