Projects per year
Abstract / Description of output
Temporally weighted linear predictive methods have recently been successfully used for robust feature extraction in speech and speaker recognition. This paper introduces their general formulation, where various efficient temporal weighting func-tions can be included in the optimization of the all-pole co-efficients of a linear predictive model. Temporal weighting is imposed by multiplying elements of instantaneous autocorrela-tion "snapshot" matrices computed from speech data. With this novel autocorrelation-snapshot formulation of weighted linear prediction, it is demonstrated that different temporal aspects of speech can be emphasized in order to enhance robustness of feature extraction in speech emotion recognition.
Original language | English |
---|---|
Title of host publication | INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association |
Subtitle of host publication | Lyon, France, August 25-29, 2013 |
Publisher | International Speech Communication Association |
Pages | 1931-1935 |
Number of pages | 5 |
Publication status | Published - 2013 |
Fingerprint
Dive into the research topics of 'Extended weighted linear prediction using the autocorrelation snapshot - a robust speech analysis method and its application to recognition of vocal emotions'. Together they form a unique fingerprint.Projects
- 1 Finished
-
HELP4MOOD:A computational distributed system to support the treatment of patients with major depression
Matheson, C. & Wolters, M.
1/01/11 → 30/06/14
Project: Research