Thesis title: “A Segment-Wise Hybrid Approach For Improved Quality Text-To-Speech Synthesis“.
Seminar Abstract: “A Segment-wise Hybrid Approach for Improved Quality Text-to-Speech Synthesis”
Seminar Presentation: “A Segment-wise Hybrid Approach for Improved Quality Text-to-Speech Synthesis”
Thesis Related Publications:
- S. Tiomkin, D. Malah, S. Shechtman,and Z. Kons, “A Hybrid Text-to-Speech System that Combines Concatenative and Statistical Synthesis Units“, IEEE Trans. Audio, Speech and Language Processing, Vol. 19, No. 5, May 2011, pp 1278-1288.
- S. Tiomkin, D. Malah, S. Shechtman, “Statistical Text-to-Speech Synthesis based on Segment-wise Representation with a Norm Constraint“, IEEE Trans. Audio, Speech and Language Processing, Vol. 18, No. 5, July 2010, pp. 1077-1082.
- S. Tiomkin and D. Malah, “Statistical Text-to-Speech Synthesis with Improved Dynamics“, Interspeech-08, Brisbane, Australia, Sept. 2008. Poster