Emotional speaker recognition in real life conditions using multiple descriptors and i-vector speaker modeling technique

Mansour, A. Ben; Chenchah, Farah; Lachiri, Zied

doi:10.1007/s11042-018-6256-2

Cited by 12 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mansour and Lachiri [16] proposed MFCC-shifted-delta-cepstral (SDC) coefficient features. In [17], Mansour et al showed MFCC-SDC features are more robust than traditional features. Satt et al [18] proposed the modified spectrogram for CNN-LSTM in noisy environment.…”

Section: Introductionmentioning

confidence: 99%

Joint enhancement and classification constraints for noisy speech emotion recognition

Sun,

Lei,

Wang

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Joint enhancement and classification constraints for noisy speech emotion recognition

Sun,

Lei,

Wang

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

“…Consequently they were fed into a SVM based classifier. In [ 26 ] also a SVM classification method was applied, this time to a mixture of MFCCs, LPCCs, shifted delta cepstrum, and RASTA-PLP (perceptual linear prediction) features, where both one against all and one against one scenario were tested.…”

Section: Introductionmentioning

confidence: 99%

On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition

Kačur

Puterka

Pavlovičová

et al. 2021

Sensors

View full text Add to dashboard Cite

Many speech emotion recognition systems have been designed using different features and classification methods. Still, there is a lack of knowledge and reasoning regarding the underlying speech characteristics and processing, i.e., how basic characteristics, methods, and settings affect the accuracy, to what extent, etc. This study is to extend physical perspective on speech emotion recognition by analyzing basic speech characteristics and modeling methods, e.g., time characteristics (segmentation, window types, and classification regions—lengths and overlaps), frequency ranges, frequency scales, processing of whole speech (spectrograms), vocal tract (filter banks, linear prediction coefficient (LPC) modeling), and excitation (inverse LPC filtering) signals, magnitude and phase manipulations, cepstral features, etc. In the evaluation phase the state-of-the-art classification method and rigorous statistical tests were applied, namely N-fold cross validation, paired t-test, rank, and Pearson correlations. The results revealed several settings in a 75% accuracy range (seven emotions). The most successful methods were based on vocal tract features using psychoacoustic filter banks covering the 0–8 kHz frequency range. Well scoring are also spectrograms carrying vocal tract and excitation information. It was found that even basic processing like pre-emphasis, segmentation, magnitude modifications, etc., can dramatically affect the results. Most findings are robust by exhibiting strong correlations across tested databases.

show abstract

“…Speech contains both linguistic and non linguistic information (Mansour et al. 2019 ). A speech signal contains information like intended message, speaker identity and emotional state of the speaker (Bhaykar et al.…”

Section: Introductionmentioning

confidence: 99%

Impact of autoencoder based compact representation on emotion detection from audio

Patel

Mankad

2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Emotion recognition from speech has its fair share of applications and consequently extensive research has been done over the past few years in this interesting field. However, many of the existing solutions aren’t yet ready for real time applications. In this work, we propose a compact representation of audio using conventional autoencoders for dimensionality reduction, and test the approach on two benchmark publicly available datasets. Such compact and simple classification systems where the computing cost is low and memory is managed efficiently may be more useful for real time application. System is evaluated on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) and the Toronto Emotional Speech Set (TESS). Three classifiers, namely, support vector machines (SVM), decision tree classifier, and convolutional neural networks (CNN) have been implemented to judge the impact of the approach. The results obtained by attempting classification with Alexnet and Resnet50 are also reported. Observations proved that this introduction of autoencoders indeed can improve the classification accuracy of the emotion in the input audio files. It can be concluded that in emotion recognition from speech, the choice and application of dimensionality reduction of audio features impacts the results that are achieved and therefore, by working on this aspect of the general speech emotion recognition model, it may be possible to make great improvements in the future.

show abstract

Emotional speaker recognition in real life conditions using multiple descriptors and i-vector speaker modeling technique

Cited by 12 publications

References 21 publications

Joint enhancement and classification constraints for noisy speech emotion recognition

Joint enhancement and classification constraints for noisy speech emotion recognition

On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition

Impact of autoencoder based compact representation on emotion detection from audio

Contact Info

Product

Resources

About