Spectral Features for Emotional Speaker Recognition

Abstract

Speaker recognition in an emotive environment is a bit challenging task because of influence of emotions in a speech. Identifying the speaker from the speech can be done by analyzing the features of the speech signal. In normal conditions, identifying a speaker is not a tedious task. Whereas, identifying the speaker in an emotional environment such as happy, sad, anger, surprise, sarcastic, fear etc. is really challenging, since speech becomes altered under emotions and noise. The spectral features of speech signal include Mel Frequency Cepstral Coefficients(MFCC), Shifted Delta Cepstral Coefficients (SDCC), spectral centroid, spectral roll off, spectral flatness, spectral contrast, spectral bandwidth, chroma-stft, zero crossing rate, root mean square energy, Linear Prediction Cepstral Coefficients (LPCC), spectral subband centroid, Teager energy based MFCC, line spectral frequencies, single frequency cepstral coefficients, formant frequencies, Power Normalized Cepstral Coefficients (PNCC), etc. The features that are extracted from the speech signal are classified using classifiers. Support Vector Machine(SVM), Gaussian Mixture Model, Gaussian Naive Bayes, K-Nearest Neighbour, Random Forest and a simple Neural Network using Keras is used for classification. The important application include security systems in which a person can be identified by biometrics that is voice of the person. The work aims to identify the speaker in an emotional environment using spectral features and classify using any of the classification techniques and to achieve a high speaker recognition rate. Feature combinations can also be used to improve accuracy. The proposed model performed better than most of the state-of-the-art methods.

Design and development of hybrid optimization enabled deep learning model for COVID-19 detection with comparative analysis with DCNN, BIAT-GRU, XGBoost

“…This feature [ 24 ] is referred as global energy of audio signal, which is estimated by, where, defines signal amplitude at amplitude, symbolizes quantity of frames in sample length, and specifies root mean square feature.…”

“…This feature defines the ratio of quantity of times the audio sample alters the value from negative to positive or else positive to negative to frame dimension [ 24 ]. The zero-crossing rate feature is denoted as .…”

Multi-Path and Group-Loss-Based Network for Speech Emotion Recognition in Multi-Domain Datasets

“…The input features for deep-learning-based SER models are generally extracted from the time or spectrum axis in units of speech segments or frames. There are various LLDs and high-level statistical functions of the LLD single features [19,20,[31][32][33]. The spectrum LLD features of speech signals include logMel filter-banks and mel-frequency cepstral coefficients (MFCC).…”

“…The spectrum LLD features of speech signals include logMel filter-banks and mel-frequency cepstral coefficients (MFCC). Zero-crossing rates and signal energies are representative time-domain features [27][28][29][30], whereas spectral roll-off and spectral centroid are classified as spectral parameters [33]. A set of multiple single features for acoustic signal processing, such as the extended Geneva Minimalistic Acoustic Parameter Set [34] and the INTERSPEECH 2010 Paralinguistic Challenge (IS10) dataset [35], is now accessible from open-source frameworks, such as OpenSmile [36].…”

An Analysis of the Impact of Spectral Contrast Feature in Speech Emotion Recognition

“…In this paper [21], the speaker is recognized in the emotional environment. Spectral features are extracted from the data and are classified.…”