Intoxicated Speech Detection by Fusion of Speaker Normalized Hierarchical Features and GMM Supervectors

  title={Intoxicated Speech Detection by Fusion of Speaker Normalized Hierarchical Features and GMM Supervectors},
  author={Daniel Bone and Matthew Black and Ming Li and Angeliki Metallinou and Sungbok Lee and Shrikanth Narayanan},
Speaker state recognition is a challenging problem due to speaker and context variability. Intoxication detection is an important area of paralinguistic speech research with potential real-world applications. In this work, we build upon a base set of various static acoustic features by proposing the combination of several different methods for this learning task. The methods include extracting hierarchical acoustic features, performing iterative speaker normalization, and using a set of GMM… CONTINUE READING
Highly Cited
This paper has 31 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 18 extracted citations


Publications referenced by this paper.
Showing 1-10 of 15 references

Praat, a system for doing phonetics by computer

P. Boersma
Glot International, vol. 5, no. 9/10, pp. 341-345, 2001. 3220 • 2001
View 9 Excerpts
Highly Influenced

Joint Factor Analysis Versus Eigenchannels in Speaker Recognition

IEEE Transactions on Audio, Speech, and Language Processing • 2007
View 4 Excerpts
Highly Influenced

Effects of alcohol on the acoustic-phonetic properties of speech: perceptual and acoustic analyses.

Alcoholism, clinical and experimental research • 1989
View 5 Excerpts
Highly Influenced

Iterative feature normalization for emotional speech detection

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2011
View 1 Excerpt

Sch iel , C . Heinrich , V . Neumeyer , “ Rhythm and Formant Features for Automatic Alcohol Det . , ” in

S. Steidl B. Schuller, A. Batliner, F. Schiel, J. Krajewski
Proc . Interspech • 2010

Similar Papers

Loading similar papers…