Enhancing support vector machine-based speech/music classification using conditional maximum a posteriori criterion

Lim, Chungsoo; Chang, Joon‐Hyuk

doi:10.1049/iet-spr.2011.0139

Cited by 14 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM maps the input patterns through a non-linear mapping into higher dimension feature space. For linearly separable data, a linear SVM is used to classify the data sets [8]. The patterns lying on the margins which are maximized are the support vectors.…”

Section: Support Vector Machinementioning

confidence: 99%

Speech/music classification using PLP and SVM

R¹

2019

int. jour. eng. com. sci

View full text Add to dashboard Cite

Automatic audio classification is very useful in audio indexing; content based audio retrieval and online audio distribution. This paper deals with the Speech/Music classification problem, starting from a set of features extracted directly from audio data. Automatic audio classification is very useful in audio indexing; content based audio retrieval and online audio distribution. The accuracy of the classification relies on the strength of the features and classification scheme. In this work Perceptual Linear Prediction (PLP) features are extracted from the input signal. After feature extraction, classification is carried out, using Support Vector Model (SVM) model. The proposed feature extraction and classification models results in better accuracy in speech/music classification.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Speech/music classification using PLP and SVM

R¹

2019

int. jour. eng. com. sci

View full text Add to dashboard Cite

show abstract

“…It's defined as the frequency where 85% of the energy in the spectrum is below that frequency. If K is the bin that fulfills (9) Then the Spectral Roll off frequency is f(K), where x(n) represents the magnitude of bin number n, and f(n) represents the center frequency of that bin.…”

Section: Spectral Roll Offmentioning

confidence: 99%

“…The time required to pass one wave at a given point is known to be as period. The number of waves passing at a time is termed as frequency [9]. Each and every complete vibration of a wave is called as cycle.…”

Section: Introductionmentioning

confidence: 99%

A Fuzzy C-Means based GMM for Classifying Speech and Music Signals

Thiruvengatanadhan¹,

Dhanalakshmi²

2014

IJCA

View full text Add to dashboard Cite

Gaussian Mixture Model (GMM) with Fuzzy c-means attempts to classify signals into speech and music. Feature extraction is done before classification. The classification accuracy mainly relays on the strength of the feature extraction techniques. Simple audio features such as Time domain and Frequency domain are adopted. The time domain features are Zero Crossing Rate (ZCR) and Short Time Energy (STE). The frequency domain features are Spectral Centroid (SC), Spectral Flux (SF), Spectral Roll-off (SR) and Spectral Entropy (SE) and Discrete Wavelet Transforms. The features thus extracted are used for classification. Commonly GMM uses Expectation Maximization (EM) algorithm to determine parameters. The proposed GMM makes use of fuzzy c-means algorithm. The fuzzy c-means algorithm is used to estimate the parameters of the GMM. Compute the probability density function and fix the Gaussian parameter. The proposed GMM model classifies the given input signal is either speech or music and compared with GMM using EM algorithm.

show abstract

“…Although ANN shows encouraging promise in FECG extraction from two ECG recordings [3,4,18], it has disadvantages of non-convex quadric minimisation which may result in multiple minima and carry the risk of over fitting [20]. Support vector machine (SVM) developed by Vapnik has gained popularity in classification and regression analysis [21][22][23][24]. SVM overcomes the limitations of ANN because it is more effective with the structural risk minimisation (SRM) principle than ANN with the traditional empirical risk minimisation principle.…”

Section: Introductionmentioning

confidence: 99%

Method of fetal electrocardiogram extraction based on ν ‐support vector regression

Han

Chen

2015

IET signal process.

View full text Add to dashboard Cite

A new method based on v-support vector regression (v-SVR) is proposed to extract the fetal electrocardiogram (FECG) from the abdominal signal recorded at the abdominal areas of the pregnant woman. The maternal electrocardiogram (MECG) component in the abdominal signal is a non-linearly transformed version of the MECG and the non-linear transform is estimated by v-SVR. The optimal estimation of the MECG component is obtained by the MECG undergoing the estimated non-linear transform. Then the FECG is extracted by subtracting the estimated MECG component from the abdominal signal. The method is validated by the experiments on both synthetic and real electrocardiogram (ECG) signals. The visual results and signal-to-noise ratio (SNR) are used to evaluate the performance of the FECG extraction methods. The experimental results indicated that the proposed method can be used for extracting the FECG from the abdominal signal.

show abstract

Enhancing support vector machine-based speech/music classification using conditional maximum a posteriori criterion

Cited by 14 publications

References 8 publications

Speech/music classification using PLP and SVM

Speech/music classification using PLP and SVM

A Fuzzy C-Means based GMM for Classifying Speech and Music Signals

Method of fetal electrocardiogram extraction based on ν ‐support vector regression

Contact Info

Product

Resources

About