Найдено 2
Ничего не найдено
Identification of Mental State Through Speech Using a Deep Learning Approach
Bera S., Dey T., Das Adhikary D., Guchhhait S., Nandi U., Faruqui N., Paul B.
Identification of one's feelings and attitude through speech is a powerful medium for expressing. Finding the emotional content in speech signals and identifying the emotions in speech utterances is crucial for researchers. This paper examines how well a deep learning-based model can identify speech emotions from two well-known datasets, TESS and RAVDESS. In this research work, a proper combination of frequency domain acoustic features of thirteen(13) Linear Predictive Coefficients (LPC) and Mel Frequency Cepstral Coefficients (MFCCs) are fed into a two-dimensional Convolutional Neural Network (CNN) model for classification. According to the experimental findings, the suggested method can recognize speech emotions with an average accuracy of 99% (TESS) and 73% (RAVDESS) for speaker-dependent (SD) speech.
Taxonomy of Music Genre Using Machine Intelligence from Feature Melting Technique
Das Adhikary D., Dey T., Bera S., Guchhhait S., Nandi U., Hasan M., Paul B.
Music is an effectual therapy in our life that makes us calm, cheerful, and excited. Music genre classification (MGC) is essential for recommendation of music and information retrieval. In our proposed work, an effective automatic musical genre classification approach has been experimented with where different features and order are fused together to get a better progressive result than the existing method. Frame-wise extraction of time-domain features(Wavelet scattering, Zero Crossing Rate, energy) and frequency-domain features(Mel Frequency Cepstral Coefficient-MFCC, pitch, Linear Predictive Coefficient-LPC) is done here. After that, the mean value of each extracted feature is put in a vector and fed to the classifier. Two well-known machine learning (ML) algorithms, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) are used to classify the GTZAN dataset. The proposed method outperformed than the existing work.
