One Solution of Extension of Mel-Frequency Cepstral Coefficients Feature Vector for Automatic Speaker Recognition
Open Access
- 16 June 2020
- journal article
- research article
- Published by Kaunas University of Technology (KTU) in Information Technology And Control
- Vol. 49 (2) , 224-236
Abstract
One extension of feature vector for automatic speaker recognition is considered in this paper. The starting feature vector consisted of 18 mel-frequency cepstral coefficients (MFCCs). Extension was done with two additional features derived from the spectrum of the speech signal. The main idea that generated this research is that it is possible to increase the efficiency of automatic speaker recognition by constructing a feature vector which tracks a real perceived spectrum in the observed speech. Additional features are based on the energy maximums in the appropriate frequency ranges of observed speech frames. In experiments, accuracy and equal error rate (EER) are compared in the case when feature vectors contain only 18 MFCCs and in cases when additional features are used. Recognition accuracy increased by around 3%. Values of EER show smaller differentiation but the results show that adding proposed additional features produced a lower decision threshold. These results indicate that tracking of real occurrences in the spectrum of the speech signal leads to more efficient automatic speaker recognizer. Determining features which track real occurrences in the speech spectrum will improve the procedure of automatic speaker recognition and enable avoiding complex models.Keywords
This publication has 24 references indexed in Scilit:
- Robust Spectral Features for Automatic Speaker Recognition in Mismatch ConditionProcedia Computer Science, 2015
- Deep belief networks for i-vector based speaker recognition2014
- Multiple windowed spectral features for emotion recognition2013
- Comparison of the automatic speaker recognition performance over standard features2012
- Automatic Birdsong Recognition with MFCC Based Syllable Feature Extraction2011
- An overview of text-independent speaker recognition: From features to supervectorsSpeech Communication, 2010
- Speaker Identification Using Instantaneous FrequenciesIEEE Transactions on Audio, Speech, and Language Processing, 2008
- Speaker Verification with Adaptive Spectral Subband CentroidsLecture Notes in Computer Science, 2007
- Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition2007
- Spectral Subband Centroids as Complementary Features for Speaker AuthenticationLecture Notes in Computer Science, 2004