Automatic Smoker Detection from Telephone Speech Signals

Amir Hossein Poorjam, Soheila Hesaraki, Saeid Safavi, Hugo Van hamme, Mohamad Hasan Bahari

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

4 Citations (Scopus)
195 Downloads (Pure)

Abstract

This paper proposes an automatic smoking habit detection from spontaneous telephone speech signals. In this method, each utterance is modeled using i-vector and non-negative factor analysis (NFA) frameworks, which yield low-dimensional representation of utterances by applying factor analysis on Gaussian mixture model means and weights respectively. Each framework is evaluated using different classification algorithms to detect the smoker speakers. Finally, score-level fusion of the i-vector-based and the NFA-based recognizers is considered to improve the classification accuracy. The proposed method is evaluated on telephone speech signals of speakers whose smoking habits are known drawn from the National Institute of Standards and Technology (NIST) 2008 and 2010 Speaker Recognition Evaluation databases. Experimental results over 1194 utterances show the effectiveness of the proposed approach for the automatic smoking habit detection task.
Original languageEnglish
Title of host publicationSpeech and Computer : 19th International Conference, SPECOM 2017, Hatfield, UK, September 12-16, 2017, Proceedings
EditorsAlexey Karpov, Rodmonga Potapova, Iosif Mporas
Number of pages11
PublisherSpringer
Publication date13 Aug 2017
Pages200-210
ISBN (Print)978-3-319-66428-6
ISBN (Electronic)978-3-319-66429-3
DOIs
Publication statusPublished - 13 Aug 2017
Event19th International Conference on Speech and Computer SPECOM 2017 - Hatfield, United Kingdom
Duration: 12 Sept 201716 Sept 2017

Conference

Conference19th International Conference on Speech and Computer SPECOM 2017
Country/TerritoryUnited Kingdom
CityHatfield
Period12/09/201716/09/2017
SeriesLecture Notes in Computer Science
Volume10458
ISSN0302-9743

Keywords

  • Smoker detection
  • i-Vector
  • Non-negative factor analysis
  • Score fusion
  • Logistic regression

Fingerprint

Dive into the research topics of 'Automatic Smoker Detection from Telephone Speech Signals'. Together they form a unique fingerprint.

Cite this