Creating and sharing knowledge for telecommunications

Project: Voice Coach for Reduced Stress

Acronym: VOCE
Main Objective:
VOCE shall develop methods and algorithms that enable the online classification of stress from live speech with the goal of providing feedback cues to the speaker in real-time to improve his communication skills. The work will focus on detecting and classifying stress in speech by leveraging advanced signal processing and machine learning techniques, complemented with psychological analysis of different aspects of stress perception.
Specifically, the tasks shall produce the following deliverables:
1) a large database of spontaneous speech samples multiply tagged for being used in the development of automatic stress recognition methods; 2) speech feature extraction algorithms that are capable of real-time performance, as well as the tagging of the samples in the database.; 3) a reduced set of features relevant for stress classification, a classification algorithm that can classify stress levels in real-time, a benchmark evaluation of the various machine learning approaches to automatic stress classification, using similar evaluation methodology and sample data set; 4) an application that integrates the results of the previous tasks and evaluate its accuracy and response times, both in laboratory settings with elicited emotions and in real-life trials.
Reference: PTDC/EEA-ELC/121018/2010
Funding: FCT/PTDC
Start Date: 01-03-2012
End Date: 01-08-2015
Team: Ana Cristina Costa Aguiar, Mariana Henriques da Silva Kaiseler, Daniel Enrique Lucani Roetter, Traian Emanuel Abrudan
Groups: Networked Systems – Po
Partners: INESC-ID
Local Coordinator: Ana Cristina Costa Aguiar
Internal Page
Associated Publications
  • 1Papers in Journals
  • J. Rodrigues, M. Kaiseler, A. Aguiar, J. Cunha, J. Barros, A Mobile Sensing Approach to Stress Detection and Memory Activation for Public Bus Drivers, IEEE Intelligent Transportation Systems Magazine, Vol. 16, No. 6, pp. 3294 - 3303, December, 2015,
    | Abstract
    | BibTex
  • 6Papers in Conferences
  • A. Aguiar, A Parallel Computing Hybrid Approach for Feature Selection, IEEE International Conference on Computer Science and Engineering CSE, Porto, Portugal, Vol. 1, pp. 1 - 1, October, 2015,
    | Abstract
    | Full text (PDF 372 KBs) | BibTex
  • M. D. Julião, J. S. Silva, A. Aguiar, G. S. Moniz, J. Ferreira, M. Batista, Speech Features for Discriminating Stress, Conf. on Telecommunications - ConfTele, Aveiro, Portugal, Vol. 1, pp. 1 - 1, September, 2015,
    | Abstract
    | Full text (PDF 217 KBs) | BibTex
  • A. Aguiar, Fine Grained Stress Assessment in Ecological Conditions, International Conf. of the IEEE Engineering in Medicine and Biology Society - EMBC, Milan, Italy, Vol. 1, pp. 1 - 1, September, 2015,
    | Abstract
    | Full text (PDF 132 KBs) | BibTex
  • M. D. Julião, J. S. Silva, A. Aguiar, HR Moniz, M. M. Batista, Speech Features for Discriminating Stress Using Branch and Bound Wrapper Search, Symp. on Languages, Applications and Technologies - SLATE, Madrid, Spain, Vol. 1, pp. 1 - 10, June, 2015,
    | Abstract
    | BibTex
  • A. Aguiar, M. Kaiseler, J. S. Silva, H. Meinedo, P. Almeida Almeida, M. D. Julião, VOCE Corpus: Ecologically Collected Speech Annotated with Physiological and Psychological Stress Assessments, ELRA International Conf. on Language Resources and Evaluation, - LREC, Reykjavik, Iceland, Vol. 978-2-9517408-8-4, pp. 1 - 6, May, 2014,
    | Abstract
    | Full text (PDF 154 KBs) | BibTex
  • A. Aguiar, M. Kaiseler, H. Meinedo, T. Abrudan, P. R. Rocha Almeida, Speech Stress Assessment using Physiological and Psychological Measures, ACM Workshop on Mobile Systems for Computational Social Science - MCSS, Zurich, Switzerland, Vol. 1, pp. 1 - 6, September, 2013,
    | Abstract
    | BibTex