Title :
Efficient Speaker Recognition Using Approximated Cross Entropy (ACE)
Author :
Aronowitz, Hagai ; Burshtein, David
Author_Institution :
T. J. Watson Res. Center, Yorktown Heights
Abstract :
Techniques for efficient speaker recognition are presented. These techniques are based on approximating Gaussian mixture modeling (GMM) likelihood scoring using approximated cross entropy (ACE). Gaussian mixture modeling is used for representing both training and test sessions and is shown to perform speaker recognition and retrieval extremely efficiently without any notable degradation in accuracy compared to classic GMM-based recognition. In addition, a GMM compression algorithm is presented. This algorithm decreases considerably the storage needed for speaker retrieval.
Keywords :
Gaussian processes; speaker recognition; Gaussian mixture modeling likelihood scoring; approximated cross entropy; compression algorithm; speaker recognition; speaker retrieval; Acoustic testing; Compression algorithms; Degradation; Entropy; Indexing; Loudspeakers; Parametric statistics; Performance evaluation; Speaker recognition; System testing; Speaker identification; speaker indexing; speaker recognition; speaker retrieval; speaker verification;
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
DOI :
10.1109/TASL.2007.902059
