Thesis Title: “Quality-Preserving Footprint-Reduction of Concatenative Text-To-Speech Synthesizers”
Seminar Abstract: “Quality-Preserving Footprint-Reduction of Concatenative Text-To-Speech Synthesizers”
Seminar Presentation: “Quality-Preserving Footprint-Reduction of Concatenative Text-To-Speech Synthesizers”
Thesis Related Publications:
- T. Shoham, D. Malah, and S. Shechtman, ”Quality Preserving Compression of a Concatenative Text-to-Speech Acoustic Database”, IEEE Trans. Audio, Speech and Language Processing,
Vol. 20, No. 3, March 2012, pp-1056-1068. - T. Shoham, D. Malah, and S. Shechtman, “Quality Preserving Compression of a Concatenative Text-To-Speech Acoustic Database“, CC Pub. #799, Dec. 2011
- T. Shoham and D. Malah, “Footprint Reduction of Concatenative Text-To-Speech Synthesizers using Polynomial Temporal Decomposition“, ISCCSP2010, Limassol, Cyprus, March 2010. Presentation