Slava Shechtman  Slava Shechtman photo         

contact information

Research staff member
Haifa Research Lab, Haifa, Israel
  

links



2018

Emphatic Speech Prosody Prediction with Deep LSTM Networks
Slava Shechtman, Moran Mordechay
ICASSP 2018, IEEE
Abstract


2017

Semi Parametric Concatenative TTS with Instant Voice Modification Capabilities
Sorin, Alexander and Shechtman, Slava and Rendeli, Asaf
Proc. Interspeech 2017, 1373--1377
Abstract


2016

Wideband Harmonic Model: Alignment and Noise Modeling for High Quality Speech Synthesis
Shechtman, Slava and Sorin, Alex
9th ISCA Speech Synthesis Workshop, pp. 229--234, 2016
Abstract


2015

Coherent modification of pitch and energy for expressive prosody implantation
Sorin, Alexander and Shechtman, Slava and Pollet, Vincent
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 4914--4918
Abstract


2014

Refined inter-segment joining in multi-form Speech synthesis
Sorin, Alexander and Shechtman, Slava and Pollet, Vincent
Fifteenth Annual Conference of the International Speech Communication Association, 2014
Abstract


2013

Transient modeling for overlap-add sinusoidal model of speech
Shechtman, Slava
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 8189--8192
Abstract


2012

Psychoacoustic segment scoring for multi-form speech synthesis
Sorin, Alexander and Shechtman, Slava and Pollet, Vincent
Thirteenth Annual Conference of the International Speech Communication Association, 2012
Abstract

Quality preserving compression of a concatenative text-to-speech acoustic database
Shoham, Tamar and Malah, David and Shechtman, Slava
IEEE Transactions on Audio, Speech, and Language Processing 20(3), 1056--1068, IEEE, 2012
Abstract


2011

A hybrid text-to-speech system that combines concatenative and statistical synthesis units
Tiomkin, Stas and Malah, David and Shechtman, Slava and Kons, Zvi
IEEE Transactions on Audio, Speech, and Language Processing 19(5), 1278--1288, IEEE, 2011
Abstract

Uniform speech parameterization for multi-form segment synthesis
Sorin, Alexander and Shechtman, Slava and Pollet, Vincent
Twelfth Annual Conference of the International Speech Communication Association, 2011
Abstract


2010

Footprint reduction of concatenative text-to-speech synthesizers using polynomial temporal decomposition
Shoham, Tamar and Malah, David and Shechtman, Slava
Communications, Control and Signal Processing (ISCCSP), 2010 4th International Symposium on, pp. 1--5
Abstract

Statistical text-to-speech synthesis based on segment-wise representation with a norm constraint
Tiomkin, Stas and Malah, David and Shechtman, Slava
IEEE Transactions on Audio, Speech, and Language Processing 18(5), 1077--1082, IEEE, 2010
Abstract

Sinusoidal model parameterization for HMM-based TTS system
Shechtman, Slava and Sorin, Alex
Eleventh Annual Conference of the International Speech Communication Association, 2010
Abstract


2009

Efficient gradient F0 tree model for prosody modeling and unit-selection, applied for the embedded US English concatenative TTS
S Shechtman, R Tachibana
Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing-Volume 00, pp. 4249--4252


2008

Statistical text-to-speech synthesis with improved dynamics
Tiomkin, Stas and Malah, David
Ninth Annual Conference of the International Speech Communication Association, 2008
Abstract

The IBM Submission to the 2008 Text-to-Speech Blizzard Challenge
R Fernandez, Z Kons, S Shechtman, Z W Shuang, R Hoory, B Ramabhadran, Y Qin
Blizzard Workshop, 2008


2007

Maximum-likelihood dynamic intonation model for concatenative text-to-speech system.
Shechtman, Slava
SSW, pp. 234--239, 2007
Abstract

Maximum-Likelihood Dynamic Intonation Model for Concatenative Text to Speech System
S Shechtman
SSW-06, pp. 234--239, 2007


2006

High quality sinusoidal modeling of wideband speech for the purposes of speech synthesis and modification
D Chazan, R Hoory, A Sagi, S Shechtman, A Sorin, Z W Shuang, R Bakis
IEEE International Conference on Acoustics, Speech and Signal Processing, 2006

The IBM submission to the 2006 Blizzard text-to-speech challenge
E. Eide, R. Fernandez, R. Hoory, W. Hamza, Z. Kons, M. Picheny, A. Sagi, S. Shechtman, Z.W. Shuang
Blizzard Workshop, 2006

Frequency Warping Based on Mapping Formant Parameters
Z W Shuang$^1$, R Bakis, S Shechtman, Y Qin$^1$
Ninth International Conference on Spoken Language Processing, 2006


2005

Speech synthesis using complex spectral modeling
D Chazan, R Hoory, Z Kons, S Shechtman, A Sorin
US Patent App. 11/ ..., 2005 - Google Patents, Google Patents
US Patent App. 11/046,911

Small footprint concatenative text-to-speech synthesis system using complex spectral envelope modeling
D Chazan, R Hoory, Z Kons, A Sagi, S Shechtman, A Sorin
Ninth European Conference on Speech Communication and Technology, 2005


2004

Efficient sub-optimal temporal decomposition with dynamic weighting of speech signals for coding applications.
Malah, David and Shechtman, Slava
INTERSPEECH, 2004

Efficient Sub-optimal Temporal Decomposition with Dynamic Weighting of Speech Signals for Coding Applications
S Shechtman, D Malah
ICSLP, 2004


Year Unknown

Advances in Spectral Parameterization for Statistical (HMM-Based) TTS
Shechtman, Slava and Sorin, Alex
pdfs.semanticscholar.org, 0
Abstract