No abstract

Singer identification is a difficult topic in music information retrieval because background instrumental music is included with singing voice which reduces performance of a system. One of the main disadvantages of the existing system is vocals and instrumental are separated manually and only vocals are used to build training model. The research presented in this paper automatically recognize a singer without separating instrumental and singing sounds using audio features like timbre coefficients, pitch class, mel frequency cepstral coefficients (MFCC), linear predictive coding (LPC) coefficients, and loudness of an audio signal from Indian video songs (IVS). Initially, various IVS of distinct playback singers (PS) are collected. After that, 53 audio features (12 dimensional timbre audio feature vectors, 12 pitch classes, 13 MFCC coefficients, 13 LPC coefficients, and 3 loudness feature vector of an audio signal) are extracted from each segment. Dimension of extracted audio features is reduced using principal component analysis (PCA) method. Playback singer model (PSM) is trained using multiclass classification algorithms like back propagation, AdaBoost.M2, k-nearest neighbor (KNN) algorithm, naïve Bayes classifier (NBC), and Gaussian mixture model (GMM). The proposed approach is tested on various combinations of dataset and different combinations of audio feature vectors with various Indian male and female PS's songs.

No abstract

No abstract

Video synopsis provides representation of the long surveillance video, while preserving the essential activities of the original video. The activity in the original video is covered into a shorter period by simultaneously displaying multiple activities, which originally occurred at different time segments. As activities are to be displayed in different time segments than original video, the process begins with extracting moving objects. Temporal median algorithm is used to model background and foreground objects are detected using background subtraction method. Each moving object is represented as a space-time activity tube in the video. The concept of genetic algorithm is used for optimized temporal shifting of activity tubes. The temporal arrangement of tubes which results in minimum collision and maintains chronological order of events is considered as the best solution. The time-lapse background video is generated next, which is used as background for the synopsis video. Finally, the activity tubes are stitched on the time-lapse background video using Poisson image editing.