Title :
Discriminative linear-transform based adaptation using minimum verification error
Author :
Shin, Sunghwan ; Jung, Ho-Young ; Kim, Tae-Yoon ; Juang, Biing-Hwang Fred
Author_Institution :
Center for Signal & Image Process., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
This paper presents an investigation of the minimum verification error linear regression (MVELR) method for discriminative linear-transform based adaptation. The MVE criterion is employed to estimate a set of discriminative linear transformations which achieve the smallest empirical average loss with the given adaptation data. The MVELR directly minimizes the total detection errors, some of which are results of characteristic mismatch in the given adaptation data. In this study, segment-based phonetic detectors reflecting an important processing layer in speech event detection are initially trained via the conventional maximum likelihood (ML) method and then refined via the general MVE method using the original training data. Then, the initial MVE-trained detectors are adapted by two kinds of adaption techniques, MLLR and MVELR, respectively, with the given adaptation data for comparison. The experiments are performed on a supervised adaptation scenario and the effectiveness of the adapted detectors is evaluated based on the total detection error. Experimental results confirm the proposed MVELR method considerably reduces the total error rate over all categories of the detectors compared to the MLLR.
Keywords :
error detection; maximum likelihood detection; regression analysis; speech processing; speech recognition; MVE criterion; detection error; discriminative linear transform based adaptation; error rate; maximum likelihood method; minimum verification error linear regression method; segment based phonetic detector; speech event detection; speech processing layer; supervised adaptation scenario; Detectors; Error analysis; Event detection; Linear regression; Maximum likelihood detection; Maximum likelihood estimation; Maximum likelihood linear regression; Performance evaluation; Speech processing; Training data; acoustic-phonetic detectors; discriminative linear transforms; minimum verification error linear regression;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5495659