2 March 1994 Tactical speaker recognition using feature and classifier fusion
Author Affiliations +
Tactical communications are inherently short and exhibit a great deal of channel variability. A novel speaker recognition technique was developed which uses on-line training to circumvent the need for excessive speaker or channel modeling. The technique incorporates both feature set fusion and classifier fusion. Separate classifiers are trained for each feature set: liftered LPC cepstra, RASTA liftered cepstra concomitant with delta cepstra. For each classifier, the results of the individual (feature) classifiers are adjudicated to rank the speakers. A final step adjudicates the results of different classifiers to determine the correct speaker.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Laurie H. Fenstermacher, Laurie H. Fenstermacher, Douglas Smith, Douglas Smith, } "Tactical speaker recognition using feature and classifier fusion", Proc. SPIE 2243, Applications of Artificial Neural Networks V, (2 March 1994); doi: 10.1117/12.169995; https://doi.org/10.1117/12.169995

Back to Top