By continuing to browse the site, you are agreeing to our use of cookies. (More details)
Portal > Offres > Offre UPR3251-LORLAM-003 - Augmentation de données acoustiques pour la reconnaissance de la parole (H/F)

Acoustic data augmentation for speech recognition (H/F)

This offer is available in the following languages:
Français - Anglais

Ensure that your candidate profile is correct before applying. Your profile information will be added to the details for each application. In order to increase your visibility on our Careers Portal and allow employers to see your candidate profile, you can upload your CV to our CV library in one click!

Faites connaître cette offre !

General information

Reference : UPR3251-LORLAM-003
Workplace : ORSAY
Date of publication : Friday, January 10, 2020
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 March 2020
Proportion of work : Full time
Remuneration : between 3400 and 4000 monthly
Desired level of education : PhD
Experience required : 5 to 10 years

Missions

The candidate will participate to the study and development of novel data augmentation methods to improve the robustness of speech recognizers in adverse acoustic conditions for the targeted applications.

The objective of the work is to address speech recognition in noisy acoustic environments and degradation due to the signal capture or transmission (telephone, HF, VHF, oxygen masks...). The target languages are English and French.

Activities

- data preparation (speech corpora)
- analysis of the speech corpora
- conception of methods/models for acoustic data transformation
- evaluation of these models on varied speech recognition tasks
- writing of reports and scientific publications

Skills

- PhD in acoustics or speech processing
- Experience with signal processing and statistical models
- Computer and programming skills (Linux, C/C++, scripting languages)
- Fluent in oral and written English

Work Context

The contract will be carried out in the Speech Processing Group at LIMSI (CNRS UP3251, Orsay, France).

Constraints and risks

nothing to signal. standard office working environment (computer)

We talk about it on Twitter!