Français Anglais
Accueil Annuaire Plan du site
Home > News du laboratoire > DIGITEO Seminar: lecture on September 27
DIGITEO Seminar: lecture on September 27
DIGITEO Seminar: lecture on September 27 DIGITEO Seminar: lecture on September 27
27 September 2012

14:30 at Supélec (amphi F3 - 05)
The statistical approach to speech recognition and natural language processing: achievements and open problems
by Hermann Ney, professor at RWTH Aachen, DIGITEO chair

The last 25 years have seen a dramatic progress in statistical methods for recognizing speech signals and for translating spoken and written language.
This lecture gives an overview of the underlying statistical methods. In particular, the lecture will focus on the remarkable fact that, for these tasks and similar tasks like handwriting recognition, the statistical approach makes use of the same four principles:
- Bayes decision rule for minimum error rate,
- Probabilistic models, e.g. Hidden Markov models or conditional random fields for handling strings of observations (like acoustic vectors for speech recognition and written words for language translation),
- training criteria and algorithms for estimating the free model parameters from large amounts of data,
- the generation or search process that generates the recognition or translation result.

Most of these methods had originally been designed for speech recognition. However, it has turned out that, with suitable modifications, the same concepts carry over to language translation and other tasks in natural language processing. This lecture will summarize the achievements and the open problems in this field.

Pour en savoir plus:
Yannis Manoussakis passed away
6 June 2021
We have just learned of the death of Yannis Manoussakis, Professor at the University of Paris-Saclay, on Saturday June 5.

He was the leader of the GALaC team and had been for many years director of the LRI, we lose a friend and a dear colleague.


Semaine du cerveau : Cerveau connecté
16 March 2021

Wizard project
1 April 2021
Innovation Area: Public Safety, IoT, Mobility