Tufekci, ZekeriyaDisken, Gokay2025-01-062025-01-0620191300-06321303-620310.3906/elk-1901-2312-s2.0-85072597726https://doi.org/10.3906/elk-1901-231https://search.trdizin.gov.tr/tr/yayin/detay/337504https://hdl.handle.net/20.500.14669/2388The 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.eninfo:eu-repo/semantics/openAccessFeature extractionspeaker recognitionspeech recognitionArticle37625Q2375833750427WOS:000486425400034Q4