Soumen Kanrar

Soumen Kanrar, Soamdeep Singha

Peer-to-Peer (P2P) network needs architectural modification for smooth and fast transportation of video content. The viewer imports chunk video objects through the proxy server. The enormous growth of user requests in a small session of time creates huge load on the VOD system. The situation requires either the proxy server streamed video-content fully or partly to the viewers. The missing chunk at the proxy server is imported from the connected peer nodes. Peers exchange chunks among themselves according to some chunk selection policy. Peer node randomly contacts another peer to download a missing chunk from the buffers during each time slot. In video streaming, when the relevant frame is required at the viewer ends that should be available at the respective proxy server. The video watcher also initiates various types of interactive operations like a move forward or skips some finite number of frames that create congestion inside the VOD system. To elevate the situation it needs an effective content delivery mechanism for smooth transportation of content. The proposed hybrid architecture is composed of P2P and mesh architecture that effectively enhances the search mechanism and content transportation in the VOD system.

Soumen Kanrar

Speaker Identification process is to identify a particular vocal cord from a set of existing speakers. In the speaker identification processes, unknown speaker voice sample targets each of the existing speakers present in the system and gives a predication. The predication may be more than one existing known speaker voice and is very close to the unknown speaker voice. The model is a Gaussian mixture model built by the extracted acoustic feature vectors from voice. The i-vector based dimension compression mapping function of the channel depended speaker, and super vector give better predicted scores according to cosine distance scoring associated with the order pair of speakers. In the order pair, the first coordinate is the unknown speaker i.e. test speaker, and the second coordinates is the existing known speaker i.e. target speaker. This paper presents the enhancement of the prediction based on i- vector in compare to the normalized set of predicted score. In the simulation, known speaker voices are collected through different channels and in different languages. In the testing, the GMM voice models, and GMM based i-Vector speaker voice models of the known speakers are used among the numbers of clusters in the test data set.

Soumen Kanrar

The automatic speaker identification procedure is used to extract features that help to identify the components of the acoustic signal by discarding all the other stuff like background noise, emotion, hesitation, etc. The acoustic signal is generated by a human that is filtered by the shape of the vocal tract, including tongue, teeth, etc. The shape of the vocal tract determines and produced, what signal comes out in real time. The analytically develops shape of the vocal tract, which exhibits envelop for the short time power spectrum. The ASR needs efficient way of extracting features from the acoustic signal that is used effectively to makes the shape of the individual vocal tract. To identify any acoustic signal in the large collection of acoustic signal i.e. corpora, it needs dimension compactness of total variability space by using the GMM mean super vector. This work presents the efficient way to implement dimension compactness in total variability space and using cosine distance scoring to predict a fast output score for small size utterance.

Aroop Mukherjee, Soumen Kanrar

Contrast enhancement is an important area of research for the image analysis. Over the decade, the researcher worked on this domain to develop an efficient and adequate algorithm. The proposed method will enhance the contrast of image using Binarization method with the help of Maximum Likelihood Estimation (MLE). The paper aims to enhance the image contrast of bimodal and multi-modal images. The proposed methodology use to collect mathematical information retrieves from the image. In this paper, we are using binarization method that generates the desired histogram by separating image nodes. It generates the enhanced image using histogram specification with binarization method. The proposed method has showed an improvement in the image contrast enhancement compare with the other image.

Soumen Kanrar

Next Generation Network (NGN) provides multimedia services over broadband based networks, which supports high definition TV (HDTV), and DVD quality video-on-demand content. The video services are thus seen as merging mainly three areas such as computing, communication, and broadcasting. It has numerous advantages and more exploration for the large-scale deployment of video-on-demand system is still needed. This is due to its economic and design constraints. It's need significant initial investments for full service provision. This paper presents different estimation for the different topologies and it require efficient planning for a VOD system network. The methodology investigates the network bandwidth requirements of a VOD system based on centralized servers, and distributed local proxies. Network traffic models are developed to evaluate the VOD system's operational bandwidth requirements for these two network architectures. This paper present an efficient estimation of the of the bandwidth requirement for the different architectures.