Automatic detection of anger in telephone speech with robust autoregressive modulation filtering

J. Pohjalainen, P. Alku

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A new system for automatic detection of angry speech is proposed. Using simulation of far-end-noise-corrupted telephone speech and the widely used Berlin database of emotional speech, autoregressive prediction of features across speech frames is shown to contribute significantly to both the clean speech performance and the robustness of the system. The autoregressive models are learned from the training data in order to capture long-term temporal dynamics of the features. Additionally, linear predictive spectrum analysis outperforms conventional Fourier spectrum analysis in terms of robustness in the computation of mel-frequency cepstral coefficients in the feature extraction stage.
Original languageEnglish
Title of host publicationAcoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages7537-7541
Number of pages5
DOIs
Publication statusPublished - 1 May 2013

Keywords

  • autoregressive processes
  • emotion recognition
  • filtering theory
  • speech recognition
  • telephony
  • Berlin database
  • anger detection
  • angry speech
  • automatic detection
  • emotional speech
  • far-end-noise-corrupted telephone speech
  • feature extraction
  • linear predictive spectrum analysis
  • mel-frequency cepstral coefficient
  • robust autoregressive modulation filtering
  • temporal dynamics
  • Databases
  • Emotion recognition
  • Feature extraction
  • Noise
  • Robustness
  • Speech
  • Speech recognition
  • emotion detection
  • speech analysis

Fingerprint Dive into the research topics of 'Automatic detection of anger in telephone speech with robust autoregressive modulation filtering'. Together they form a unique fingerprint.

Cite this