Analysis and comparison of two speech feature extraction/compensation algorithms

Abstract

Two feature extraction and compensation algorithms, feature-space minimum phone error (fMPE), which contributed to the recent significant progress in conversational speech recognition, and stereo-based piecewise linear compensation for environments (SPLICE), which has been used successfully in noise-robust speech recognition, are analyzed and compared. These two algorithms have been developed by very different motivations and been applied to very different speech-recognition tasks as well. While the mathematical construction of the two algorithms is ostensibly different, in this report, we establish direct link between them. We show that both algorithms in the run-time operation accomplish feature extraction/compensation by adding posterior-based weighted sum of vectors, or equivalently the column vectors in the fMPE projection matrix, to the original, uncompensated features. Although the published fMPE algorithm empirically motivates such feature extraction, operation as a reasonable starting point for our analysis proves that it is natural consequence of the rigorous minimum mean square error (MMSE) optimization rule as developed in SPLICE. Further, we review and compare related speech-recognition results with the use of fMPE and SPLICE algorithms. The results demonstrate the effectiveness of discriminative training on the feature extraction parameters (i.e., projection matrix in fMPE and equivalently correction vectors in SPLICE). The analysis and comparison of the two algorithms provide useful insight into the strong success of fMPE and point to further algorithm improvement and extension.