Abstract: Systems and methods for sensitive audio zone rearrangement are provided that protects confidential and sensitive information such as user identifier during query processing and authentication. The sensitive information rearrangement system generates or permutes the actual user identifier in a privacy preserving manner. The sensitive information is extracted from an input being either a speech or DTMF tones, and a virtual user identifier is generated in real time, that is specific to a transaction to be performed, or a query initiation by a user in real-time. The sensitive information is rearranged which can be either DTMF tone or speech of user to generate the virtual user identifier.

Abstract: The disclosure generally relates to transcription of spoken words, and more particularly to a system and method for transcription of spoken words using multilingual mismatched words. The process comprises collection of multi-scripted noisy transcriptions of the spoken word obtained from workers of the multilingual mismatched crowd unfamiliar with the spoken language. The collected words are mapped to a phoneme sequence in the source language using script specific graphemes to phoneme model. Further, it builds a multi-scripted transcription script specific, worker specific and a global insertion-deletion-substitution (IDS) channel. Furthermore, the disclosure also determines reputation of workers to allocate the transcription task. Determination of reputation is based on word belief.

Abstract: System and method for layer-wise training of deep neural networks (DNNs) are disclosed. In an embodiment, multiple labelled images are received at a layer of multiple layers of a DNN. Further, the labelled images are pre-processed. The pre-processed images are then transformed based on a predetermined weight matrix to obtain feature representation of the pre-processed images at the layer, the feature representation comprise feature vectors and associated labels. Furthermore, kernel similarity between the feature vectors is determined based on a predefined kernel function. Moreover, a Gaussian kernel matrix is determined based on the kernel similarity. In addition, an error function is computed based on the predetermined weight matrix and the Gaussian kernel matrix. Also, a weight matrix associated with the layer is computed based on the error function and predetermined weight matrix, thereby training the layer of the multiple layers.

Abstract: System and method for layer-wise training of deep neural networks (DNNs) are disclosed. In an embodiment, multiple labelled images are received at a layer of multiple layers of a DNN. Further, the labelled images are pre-processed. The pre-processed images are then transformed based on a predetermined weight matrix to obtain feature representation of the pre-processed images at the layer, the feature representation comprise feature vectors and associated labels. Furthermore, kernel similarity between the feature vectors is determined based on a predefined kernel function. Moreover, a Gaussian kernel matrix is determined based on the kernel similarity. In addition, an error function is computed based on the predetermined weight matrix and the Gaussian kernel matrix. Also, a weight matrix associated with the layer is computed based on the error function and predetermined weight matrix, thereby training the layer of the multiple layers.

Abstract: The disclosure generally relates to transcription of spoken words, and more particularly to a system and method for transcription of spoken words using multilingual mismatched words. The process comprises collection of multi-scripted noisy transcriptions of the spoken word obtained from workers of the multilingual mismatched crowd. The collected words are mapped to a phoneme sequence in the source language using script specific graphemes to phoneme model. Further, it builds a multi-scripted transcription script specific, worker specific and a global insertion-deletion-substitution (IDS) channel. Furthermore, the disclosure also determines reputation of workers to allocate the transcription task. Determination of reputation is based on word belief.

Abstract: This disclosure relates generally to image processing, and more particularly to system and method for image inpainting. In one embodiment, a method for image inpainting includes aligning a plurality of multi-view images of a scene with respect to a reference image to obtain a plurality of aligned multi-view images. A region of interest (ROI) representing a region to be removed from the reference image for image inpainting is selected. A dictionary is created by selecting image-patches from the reference image and the plurality of aligned multi-view images, and 3D rotations thereof. A priority value of each of a plurality of pixels of the ROI is created. The ROI is systematically reconstructed in the reference image based at least on the priority values of the plurality of pixels and the dictionary by computing a linear combination of two or more image-patches selected from the plurality of image-patches of the dictionary.

Abstract: Systems and methods for sensitive audio zone rearrangement are provided that protects confidential and sensitive information such as user identifier during query processing and authentication. The sensitive information rearrangement system generates or permutes the actual user identifier in a privacy preserving manner. The sensitive information is extracted from an input being either a speech or DTMF tones, and a virtual user identifier is generated in real time, that is specific to a transaction to be performed, or a query initiation by a user in real-time. The sensitive information is rearranged which can be either DTMF tone or speech of user to generate the virtual user identifier.

Abstract: This disclosure relates generally to image processing, and more particularly to system and method for image inpainting. In one embodiment, a method for image inpainting includes aligning a plurality of multi-view images of a scene with respect to a reference image to obtain a plurality of aligned multi-view images. A region of interest (ROI) representing a region to be removed from the reference image for image inpainting is selected. A dictionary is created by selecting image-patches from the reference image and the plurality of aligned multi-view images, and 3D rotations thereof. A priority value of each of a plurality of pixels of the ROI is created. The ROI is systematically reconstructed in the reference image based at least on the priority values of the plurality of pixels and the dictionary by computing a linear combination of two or more image-patches selected from the plurality of image-patches of the dictionary.