Aarti Bakshi
Support vector machineLanguage identificationPhoneticsWindow functionMel-frequency cepstrumPattern recognitionComputational complexity theoryUtteranceDravidian languagesVariation (linguistics)Classifier (linguistics)Speech recognitionPreprocessorComputer scienceArtificial neural networkFeature extractionMixture modelFeature (computer vision)Identification (information)Polynomial
Publications 3
Gaussian Mixture Model-Universal Background Model (GMM‑UBM) supervectors are used to identify spoken Indian languages. The supervectors are calculated from short-time MFCC, its first and second derivatives. The UBM builds a generalized Indian language model, and mean adaptation transforms it to a duration normalized language-specific GMM. Multi-class support vector machine and artificial neural network classifiers are used to identify language labels from the supervectors. Experimental evaluatio...
#1Aarti BakshiH-Index: 1
#2Sunil Kumar Kopparapu (Tata Consultancy Services)H-Index: 8
Indian languages are phonetic in nature; phonetics is branch of linguistics which studies the structure of human language sound. Acoustic phonetic features associated with languages play an important role in spoken language identification. In this paper, Gaussian Mixture Model supervectors is used to capture acoustic phonetic variation in Indian languages. Mel frequency cepstral coefficient (MFCC) with delta coefficients is used to represent the language specific acoustic phonetic information of...
#1Aarti BakshiH-Index: 1
#2Sunil Kumar Kopparapu (Tata Consultancy Services)H-Index: 8
Last. Shikha NemaH-Index: 2
view all 4 authors...
Speech is one of the most popular parameter used to identify a speaker by her spoken phrase. Feature extraction from speech is a necessary first step in a speaker identification process. Traditionally computation of the Mel Frequency Cepstral Coefficient (MFCC) features use hamming window, as a preprocessing step to reduce spectral leakages. However, hamming window results in reasonable side lobes along with the desired main lobe. This paper deals with a modified algorithm to compute MFCC featur...
4 CitationsSource
Close Researchers