The exploitation of Multiple Feature Extraction Techniques for Speaker Identification in Emotional States under Disguised Voices

@article{Hindawi2021TheEO,
  title={The exploitation of Multiple Feature Extraction Techniques for Speaker Identification in Emotional States under Disguised Voices},
  author={Noor Ahmad Al Hindawi and Ismail Shahin and Ali Bou Nassif},
  journal={2021 14th International Conference on Developments in eSystems Engineering (DeSE)},
  year={2021},
  pages={269-273}
}
  • N. HindawiI. ShahinA. B. Nassif
  • Published 7 December 2021
  • Computer Science
  • 2021 14th International Conference on Developments in eSystems Engineering (DeSE)
Due to improvements in artificial intelligence, speaker identification (SI) technologies have brought a great direction and are now widely used in a variety of sectors. One of the most important components of SI is feature extraction, which has a substantial impact on the SI process and performance. As a result, numerous feature extraction strategies are thoroughly investigated, contrasted, and analyzed. This article exploits five distinct feature extraction methods for speaker identification… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 38 REFERENCES

Speaker Identification for Disguised Voices Based on Modified SVM Classifier

This work demonstrates that modified SVM is superior to other classical classifiers such as: K-Nearest Neighbor (KNN), Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), Naïve Bayes (NB), and the conventional SVM.

Identifying speakers using their emotion cues

The proposed approach is based on a two-stage recognizer that combines and integrates both emotion recognizer and speaker recognizer into one recognizer, which employs both Hidden Markov Models and Suprasegmental HiddenMarkov Models as classifiers.

A pitch synchronous feature extraction method for speaker recognition

A novel feature extraction method in the form of a typical conventional feature, Mel frequency cepstral coefficients, but a flexible segmentation to reduce spectral mismatch between training and testing processes is presented.

On the Use of Distributed DCT in Speaker Identification

The proposed method improves the performance over baseline MFCC based SI system for various number of filters in the filterbank and includes the DCT in a distributed manner.

Acoustic analysis of disguised voices with raised and lowered pitch

  • Cuiling Zhang
  • Physics
    2012 8th International Symposium on Chinese Spoken Language Processing
  • 2012
The acoustic properties of disguised voices with raised and lowered pitch from 11 Chinese male speakers are investigated and some systematic changes of parameters provide clues for forensic voice comparison.

Feature Extraction Methods LPC , PLP and MFCC In Speech Recognition

Neural network is described in this paper with LPC, PLP and MFCC parameters, which considers the nature of speech while it extracts the features and predicts the future features based on previous features.

Voice Disguise and Automatic Detection: Review and Perspectives

This study focuses on the question of voice disguise and its detection and describes the main indicators proposed in the literature to distinguish a disguised voice from the original voice, and proposes some perspectives based on disordered and emotional speech.

Emarati speaker identification

In this work we focus on Emarati speaker identification systems in neutral talking environments based on each of Vector Quantization (VQ), Gaussian Mixture Models (GMMs), and Hidden Markov Models

Using information theoretic vector quantization for inverted MFCC based speaker verification

  • S. MemonM. LechLing He
  • Computer Science
    2009 2nd International Conference on Computer, Control and Communication
  • 2009
A search of alternative classification and feature extraction methods of similar classification efficiency but overcoming some of the problems of the classical methods was undertaken and the best feature extraction method was proven to be the MFCC/IMFCC fusion.