A Study of Speech, Speaker and Emotion Recognition Using Mel Frequency Cepstrum Coefficients and Support Vector Machines

Rajasekhar, Ashwini; Hota, Malaya Kumar

doi:10.1109/iccsp.2018.8524451

Cited by 20 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SVM classifier that has variable kernel functions, is one of the widely used optimization-based classifiers. The kernel functions increase the sample space to a higher dimension so that data can be separated linearly and also the kernels reduce the computational complexity by increasing the dimension [6], [33], [49]. The nonlinear classifier, SVM calculates the boundary of the decision precisely for speaker-independent and small-sized sample applications [6].…”

Section: Methodsmentioning

confidence: 99%

“…ML involves two processes, training and testing. The conventional classifiers are naive Bayes [6], decision trees (DT) [6], artificial neural networks (ANN) [8], hidden Markov model (HMM) [16], Gaussian mixture model (GMM) [24], extreme Learning machine (ELM) [25], knearest neighbor (KNN) [25], incomplete sparse least square regression [32], and support vector machines (SVM) [33]. Kmeans algorithm is an unsupervised clustering method; other classifiers may be used with in ensemble methods [34].…”

Section: Classification In the Ser Literaturementioning

confidence: 99%

“…In smaller samples of training data, ANN gives better results than GMM and HMM [8], [32]. SVM is a statistical and supervised ML algorithm; it decomposes linear and nonlinear features of the input data; the features are transformed to a high dimensional vector space by a kernel function [33]. KNN is a distance-based, supervised ML algorithm [32].…”

Section: Classification In the Ser Literaturementioning

confidence: 99%

See 2 more Smart Citations

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

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

Section: Methodsmentioning

confidence: 99%

Section: Classification In the Ser Literaturementioning

confidence: 99%

Section: Classification In the Ser Literaturementioning

confidence: 99%

See 1 more Smart Citation

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

“…MFCC is one of the most popular speech feature to be utilized for SER, as shown in research [1][2][3][4][5][6][7]. This common usage enables us to benchmark the results.…”

Section: Mel-frequency Cepstral Coefficients (Mfccs) Feature Extractionmentioning

confidence: 99%

“…The recent trend of performing SER is to employ machine learning for the system to learn the speech emotion feature patterns. There are many popular machine learning models such as support vector machine (SVM) [1][2][3], Hidden Markov Model (HMM) [4,5], or artificial neural networks in many forms such as convolutional neural networks (CNN) [6,7] or recurrent neural network (RNN) [8]. A neural network can be considered deep when it uses more than a single layer.…”

Section: Introductionmentioning

confidence: 99%

On the use of voice activity detection in speech emotion recognition

et al. 2019

View full text Add to dashboard Cite

Emotion recognition through speech has many potential applications, however the challenge comes from achieving a high emotion recognition while using limited resources or interference such as noise. In this paper we have explored the possibility of improving speech emotion recognition by utilizing the voice activity detection (VAD) concept. The emotional voice data from the Berlin Emotion Database (EMO-DB) and a custom-made database LQ Audio Dataset are firstly preprocessed by VAD before feature extraction. The features are then passed to the deep neural network for classification. In this paper, we have chosen MFCC to be the sole determinant feature. From the results obtained using VAD and without, we have found that the VAD improved the recognition rate of 5 emotions (happy, angry, sad, fear, and neutral) by 3.7% when recognizing clean signals, while the effect of using VAD when training a network with both clean and noisy signals improved our previous results by 50%.

show abstract