Turkish Journal of Electrical Engineering and Computer Sciences
Abstract
The feature extraction process is a fundamental part of speech processing. Mel frequency cepstral coefficients (MFCCs) are the most commonly used feature types in the speech/speaker recognition literature. However, the MFCC framework may face numerical issues or dynamic range problems, which decreases their performance. A practical solution to these problems is adding a constant to filter-bank magnitudes before log compression, thus violating the scale-invariant property. In this work, a magnitude normalization and a multiplication constant are introduced to make the MFCCs scale-invariant and to avoid dynamic range expansion of nonspeech frames. Speaker verification experiments are conducted to show the effectiveness of the proposed scheme.
DOI
10.3906/elk-1901-231
Keywords
Feature extraction, speaker recognition, speech recognition
First Page
3758
Last Page
3762
Recommended Citation
TÜFEKCİ, Z, & DİŞKEN, G (2019). Scale-invariant MFCCs for speech/speaker recognition. Turkish Journal of Electrical Engineering and Computer Sciences 27 (5): 3758-3762. https://doi.org/10.3906/elk-1901-231
Included in
Computer Engineering Commons, Computer Sciences Commons, Electrical and Computer Engineering Commons
