Automatic Speaker Recognition Using Mel-Frequency Cepstral Coefficients Through Machine Learning

Creative Commons License

Ayvaz U., GÜRÜLER H., Khan F., Ahmed N., Whangbo T., Bobomirzaevich A. A.

CMC-COMPUTERS MATERIALS & CONTINUA, cilt.71, sa.3, ss.5511-5521, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 71 Sayı: 3
  • Basım Tarihi: 2022
  • Doi Numarası: 10.32604/cmc.2022.023278
  • Dergi Adı: CMC-COMPUTERS MATERIALS & CONTINUA
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Communication Abstracts, Compendex, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.5511-5521
  • Anahtar Kelimeler: Automatic speaker recognition, human voice recognition, spatial pattern recognition, MFCCs, spectrogram, machine learning, artificial intelligence, MFCC
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

Automatic speaker recognition (ASR) systems are the field of Human-machine interaction and scientists have been using feature extraction and feature matching methods to analyze and synthesize these signals. One of the most commonly used methods for feature extraction is Mel Frequency Cepstral Coefficients (MFCCs). Recent researches show that MFCCs are successful in processing the voice signal with high accuracies. MFCCs represents a sequence of voice signal-specific features. This experimental analysis is proposed to distinguish Turkish speakers by extracting the MFCCs from the speech recordings. Since the human perception of sound is not linear, after the filterbank step in the MFCC method, we converted the obtained log filter banks into decibel (dB) features-based spectrograms without applying the Discrete Cosine Transform (DCT). A new dataset was created with converted spectrogram into a 2-D array. Several learning algorithms were implemented with a 10-fold cross-validation method to detect the speaker. The highest accuracy of 90.2% was achieved using Multi-layer Perceptron (MLP) with tanh activation function. The most important output of this study is the inclusion of human voice as a new feature set.