Learning vocal tract variables with multi-task kernels

Hachem Kadri 1 Emmanuel Duflos 2 Philippe Preux 1, 3, 4
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
2 LAGIS-SI
LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : The problem of acoustic-to-articulatory speech inversion continues to be a challenging research problem which sig- nificantly impacts automatic speech recognition robustness and accuracy. This paper presents a multi-task kernel based method aimed at learning Vocal Tract (VT) variables from the Mel-Frequency Cepstral Coefficients (MFCCs). Unlike usual speech inversion techniques based on individual esti- mation of each tract variable, the key idea here is to consider all the target variables simultaneously to take advantage of the relationships among them and then improve learning per- formance. The proposed method is evaluated using synthetic speech dataset and corresponding tract variables created by the TAsk Dynamics Application (TADA) model and com- pared to the hierarchical ε-SVR speech inversion technique.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00826050
Contributor : Preux Philippe <>
Submitted on : Tuesday, June 4, 2013 - 9:18:41 AM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Thursday, September 5, 2013 - 4:19:23 AM

File

ICASSP2011.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00826050, version 1

Collections

Citation

Hachem Kadri, Emmanuel Duflos, Philippe Preux. Learning vocal tract variables with multi-task kernels. 36th International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, Czech Republic. ⟨hal-00826050⟩

Share

Metrics

Record views

511

Files downloads

252