Wavelet based feature combination for recognition of emotions

Interpreting a speech signal is quite challenging because it consists of different frequencies and features that vary according to emotions. Although different algorithms are being developed in the speech emotion recognition (SER) domain, the success rates vary according to the spoken languages, emotions, and databases. In this study, a new lightweight effective SER method has been developed that has low computational complexity. This method, called 1BTPDN, is applied on RAVDESS, EMO-DB, SAVEE, and EMOVO databases. First, low-pass filter coefficients are obtained by applying a one-dimensional discrete wavelet transform on the raw audio data. The features are extracted by applying textural analysis methods, a one-dimensional local binary pattern, and a one-dimensional local ternary pattern to each filter. Using neighborhood component analysis, the most dominant 1024 features are selected from 7680 features while the other features are discarded. These 1024 features are selected as the input of the classifier which is a thirddegree polynomial kernel-based support vector machine. The success rates of the 1BTPDN reached 95.16%, 89.16%, 76.67%, and 74.31% in the RAVDESS, EMO-DB, SAVEE, and EMOVO databases, respectively. The recognition rates are higher compared to many textural, acoustic, and deep learning state-of-the-art SER methods. INDEX TERMS Discrete wavelet transform, local binary pattern, local ternary pattern, neighborhood component analysis, speech emotion recognition.

show abstract

“…Reference [58] which uses neural network, [59] and [60] which use deep learning algorithms have more successful results than 1BTPDN method.…”

Section: Discussionmentioning

confidence: 99%

A Speech Emotion Recognition Model Based on Multi-Level Local Binary and Local Ternary Patterns

Sönmez

Varol

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [19], sub-band spectral centroid Weighted Wavelet Packet Cepstral Coefficients (W-WPCC) were proposed and were fused with Wavelet Packet Cepstral Coefficients (WPCC) and prosodic and voice quality features to deal with white Gaussian noise. In [20], Linear Predictive Cepstral Coefficients (LPCC) and MFCCs were derived from wavelet sub-bands and were fused with baseline LPCCs and MFCCs. The resulting feature dimension was reduced using the vector quantization method, and the obtained feature vector was used as input to a Radial Basis Function Neural Network (RBFNN) classifier.…”

Section: Review Of Feature Level Fusion Based Sermentioning

confidence: 99%

An Investigation of a Feature-Level Fusion for Noisy Speech Emotion Recognition

2019

View full text Add to dashboard Cite

Because one of the key issues in improving the performance of Speech Emotion Recognition (SER) systems is the choice of an effective feature representation, most of the research has focused on developing a feature level fusion using a large set of features. In our study, we propose a relatively low-dimensional feature set that combines three features: baseline Mel Frequency Cepstral Coefficients (MFCCs), MFCCs derived from Discrete Wavelet Transform (DWT) sub-band coefficients that are denoted as DMFCC, and pitch based features. Moreover, the performance of the proposed feature extraction method is evaluated in clean conditions and in the presence of several real-world noises. Furthermore, conventional Machine Learning (ML) and Deep Learning (DL) classifiers are employed for comparison. The proposal is tested using speech utterances of both of the Berlin German Emotional Database (EMO-DB) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) speech databases through speaker independent experiments. Experimental results show improvement in speech emotion detection over baselines.

show abstract

Section: Corresponding Author: Ihsan Al-hassani Department Of Telecomentioning

confidence: 99%

“…accuracy (Palo and Mohanty, 2017). Experiments show that the combined features exhibit superior performance in terms of Mean Square Error (MSE) for classification task using Radial Basis Function Network (RBFNN) classifier (Palo and Mohanty, 2017). Wang et al (2018) proposed a feature compression algorithm entitled Suppression by Selecting Wavelets (SSW), to achieve the two main goals of Distributed Speech Recognition (DSR): minimizing memory and device requirements.…”

Section: Corresponding Author: Ihsan Al-hassani Department Of Telecomentioning

confidence: 99%

A New Robust Resonance Based Wavelet Decomposition Cepstral Features for Phoneme Recoszgnition

Al-Hassani¹,

Al-Dakkak²,

Assami³

2019

Res. J. Applied Sci.

View full text Add to dashboard Cite

Robust Automatic Speech Recognition (ASR) is a challenging task that has been an active research subject for the last 20 years. And still results are very modest in the highly noisy environments. In this study, we propose a new speech parameterization method based on concatenating two wavelet packet decompositions, one decomposition using low Q-factor wavelet and another with high Q-factor wavelet, to extract speech features suitable for ASR task in noisy conditions. Experiments on TIMIT dataset for phonemes recognition show that the proposed wavelet-based features outperform MFCC in all noisy conditions.

show abstract

Wavelet based feature combination for recognition of emotions

Cited by 60 publications

References 14 publications

A Speech Emotion Recognition Model Based on Multi-Level Local Binary and Local Ternary Patterns

A Speech Emotion Recognition Model Based on Multi-Level Local Binary and Local Ternary Patterns

An Investigation of a Feature-Level Fusion for Noisy Speech Emotion Recognition

A New Robust Resonance Based Wavelet Decomposition Cepstral Features for Phoneme Recoszgnition

Contact Info

Product

Resources

About