Verification of multi-class recognition decision using classification approach

We investigate various strategies to improve the utterance verification performance using a 2-class pattern classifier. They include utilizing N-best candidate scores, modifying segmentation boundaries, applying background and out-of-vocabulary filler models, incorporating contexts, and minimizing verification errors via discriminative training. A connected-digit database containing utterances recorded in a noisy, moving car with a hands-free microphone mounted on a sun-visor is used to evaluate the verification performance. The equal error rate (EER) of word verification is employed as the performance measure in our evaluations. All factors considered in our study and their effects on the verification performance are presented in detail. The EER is reduced from 29%, using the standard likelihood ratio test, down to 21.4%, when all enhancements are integrated together.