arXiv subjects

Bhiksha Raj

Publications and source records attributed to Bhiksha Raj.

At least 199 records · Page 11Linked to original sources

arXiv2017

Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully supervised data where all labeled instances are available. In weakly supervised learning only data is weakly labeled which prevents one from directly applying supervised learning methods. Our proposed framework is motivated by the fact that a small amount of strongly labeled data can give considerable improvement over only weakly supervised learning. The primary problem domain focus of this paper is acoustic event and scene detection in audio recordings. We first propose a naive formulation for leveraging labeled data in both forms. We then propose a more general framework for Supervised and Weakly Supervised Learning (SWSL). Based on this general framework, we propose a graph based approach for SWSL. Our main method is based on manifold regularization on graphs in which we show that the unified learning can be formulated as a constraint optimization problem which can be solved by iterative concave-convex procedure (CCCP). Our experiments show that our proposed framework can address several concerns of audio content analysis using weakly labeled data.

cs.LG↗

arXiv2017

Discovering Sound Concepts and Acoustic Relations In Text

In this paper we describe approaches for discovering acoustic concepts and relations in text. The first major goal is to be able to identify text phrases which contain a notion of audibility and can be termed as a sound or an acoustic concept. We also propose a method to define an acoustic scene through a set of sound concepts. We use pattern matching and parts of speech tags to generate sound concepts from large scale text corpora. We use dependency parsing and LSTM recurrent neural network to predict a set of sound concepts for a given acoustic scene. These methods are not only helpful in creating an acoustic knowledge base but in the future can also directly help acoustic event and scene detection research.

cs.SD↗

arXiv2016

Audio Content based Geotagging in Multimedia

In this paper we propose methods to extract geographically relevant information in a multimedia recording using its audio. Our method primarily is based on the fact that urban acoustic environment consists of a variety of sounds. Hence, location information can be inferred from the composition of sound events/classes present in the audio. More specifically, we adopt matrix factorization techniques to obtain semantic content of recording in terms of different sound classes. These semantic information are then combined to identify the location of recording.

cs.SD↗

arXiv2016

Environmental Noise Embeddings for Robust Speech Recognition

We propose a novel deep neural network architecture for speech recognition that explicitly employs knowledge of the background environmental noise within a deep neural network acoustic model. A deep neural network is used to predict the acoustic environment in which the system in being used. The discriminative embedding generated at the bottleneck layer of this network is then concatenated with traditional acoustic features as input to a deep neural network acoustic model. Through a series of experiments on Resource Management, CHiME-3 task, and Aurora4, we show that the proposed approach significantly improves speech recognition accuracy in noisy and highly reverberant environments, outperforming multi-condition training, noise-aware training, i-vector framework, and multi-task learning on both in-domain noise and unseen noise.

cs.CL↗

arXiv2016

Privacy Preserving Distance Computation using Somewhat-trusted Third Parties

A critically important component of most signal processing procedures is that of computing the distance between signals. In multi-party processing applications where these signals belong to different parties, this introduces privacy challenges. The signals may themselves be private, and the parties to the computation may not be willing to expose them. Solutions proposed to the problem in the literature generally invoke homomorphic encryption schemes, secure multi-party computation, or other cryptographic methods which introduce significant computational complexity into the proceedings, often to the point of making more complex computations requiring repeated computations unfeasible. Other solutions invoke third parties, making unrealistic assumptions about their trustworthiness. In this paper we propose an alternate approach, also based on third party computation, but without assuming as much trust in the third party. Individual participants to the computation "secure" their data through a proposed secure hashing scheme with shared keys, prior to sharing it with the third party. The hashing ensures that the third party cannot recover any information about the individual signals or their statistics, either from analysis of individual computations or their long-term aggregate patterns. We provide theoretical proof of these properties and empirical demonstration of the feasibility of the computation.

cs.CR↗

arXiv2016

Experiments on the DCASE Challenge 2016: Acoustic Scene Classification and Sound Event Detection in Real Life Recording

In this paper we present our work on Task 1 Acoustic Scene Classi- fication and Task 3 Sound Event Detection in Real Life Recordings. Among our experiments we have low-level and high-level features, classifier optimization and other heuristics specific to each task. Our performance for both tasks improved the baseline from DCASE: for Task 1 we achieved an overall accuracy of 78.9% compared to the baseline of 72.6% and for Task 3 we achieved a Segment-Based Error Rate of 0.76 compared to the baseline of 0.91.

cs.SD↗

arXiv2016

Features and Kernels for Audio Event Recognition

One of the most important problems in audio event detection research is absence of benchmark results for comparison with any proposed method. Different works consider different sets of events and datasets which makes it difficult to comprehensively analyze any novel method with an existing one. In this paper we propose to establish results for audio event recognition on two recent publicly-available datasets. In particular we use Gaussian Mixture model based feature representation and combine them with linear as well as non-linear kernel Support Vector Machines.

cs.SD↗

arXiv2016

Audio Event Detection using Weakly Labeled Data

Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data. However, the labels available for majority of multimedia data are generally weak and do not provide sufficient detail for such methods to be employed. In this paper we propose a framework for learning acoustic event detectors using only weakly labeled data. We first show that audio event detection using weak labels can be formulated as an Multiple Instance Learning problem. We then suggest two frameworks for solving multiple-instance learning, one based on support vector machines, and the other on neural networks. The proposed methods can help in removing the time consuming and expensive process of manually annotating data to facilitate fully supervised learning. Moreover, it can not only detect events in a recording but can also provide temporal locations of events in the recording. This helps in obtaining a complete description of the recording and is notable since temporal information was never known in the first place in weakly labeled data.

cs.SD↗

arXiv2016

Weakly Supervised Scalable Audio Content Analysis

Audio Event Detection is an important task for content analysis of multimedia data. Most of the current works on detection of audio events is driven through supervised learning approaches. We propose a weakly supervised learning framework which can make use of the tremendous amount of web multimedia data with significantly reduced annotation effort and expense. Specifically, we use several multiple instance learning algorithms to show that audio event detection through weak labels is feasible. We also propose a novel scalable multiple instance learning algorithm and show that its competitive with other multiple instance learning algorithms for audio event detection tasks.

cs.SD↗

arXiv2016

Learning Model-Based Sparsity via Projected Gradient Descent

Several convex formulation methods have been proposed previously for statistical estimation with structured sparsity as the prior. These methods often require a carefully tuned regularization parameter, often a cumbersome or heuristic exercise. Furthermore, the estimate that these methods produce might not belong to the desired sparsity model, albeit accurately approximating the true parameter. Therefore, greedy-type algorithms could often be more desirable in estimating structured-sparse parameters. So far, these greedy methods have mostly focused on linear statistical models. In this paper we study the projected gradient descent with non-convex structured-sparse parameter model as the constraint set. Should the cost function have a Stable Model-Restricted Hessian the algorithm produces an approximation for the desired minimizer. As an example we elaborate on application of the main results to estimation in Generalized Linear Model.

stat.ML↗

arXiv2015

Handcrafted Local Features are Convolutional Neural Networks

Image and video classification research has made great progress through the development of handcrafted local features and learning based features. These two architectures were proposed roughly at the same time and have flourished at overlapping stages of history. However, they are typically viewed as distinct approaches. In this paper, we emphasize their structural similarities and show how such a unified view helps us in designing features that balance efficiency and effectiveness. As an example, we study the problem of designing efficient video feature learning algorithms for action recognition. We approach this problem by first showing that local handcrafted features and Convolutional Neural Networks (CNNs) share the same convolution-pooling network structure. We then propose a two-stream Convolutional ISA (ConvISA) that adopts the convolution-pooling structure of the state-of-the-art handcrafted video feature with greater modeling capacities and a cost-effective training algorithm. Through custom designed network structures for pixels and optical flow, our method also reflects distinctive characteristics of these two data sources. Our experimental results on standard action recognition benchmarks show that by focusing on the structure of CNNs, rather than end-to-end training methods, we are able to design an efficient and powerful video feature learning algorithm.

cs.CV↗

arXiv2015

A Survey: Time Travel in Deep Learning Space: An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas

This report will show the history of deep learning evolves. It will trace back as far as the initial belief of connectionism modelling of brain, and come back to look at its early stage realization: neural networks. With the background of neural network, we will gradually introduce how convolutional neural network, as a representative of deep discriminative models, is developed from neural networks, together with many practical techniques that can help in optimization of neural networks. On the other hand, we will also trace back to see the evolution history of deep generative models, to see how researchers balance the representation power and computation complexity to reach Restricted Boltzmann Machine and eventually reach Deep Belief Nets. Further, we will also look into the development history of modelling time series data with neural networks. We start with Time Delay Neural Networks and move further to currently famous model named Recurrent Neural Network and its extension Long Short Term Memory. We will also briefly look into how to construct deep recurrent neural networks. Finally, we will conclude this report with some interesting open-ended questions of deep neural networks.

cs.LG↗

arXiv2015

Privacy-Preserving Multi-Document Summarization

State-of-the-art extractive multi-document summarization systems are usually designed without any concern about privacy issues, meaning that all documents are open to third parties. In this paper we propose a privacy-preserving approach to multi-document summarization. Our approach enables other parties to obtain summaries without learning anything else about the original documents' content. We use a hashing scheme known as Secure Binary Embeddings to convert documents representation containing key phrases and bag-of-words into bit strings, allowing the computation of approximate distances, instead of exact ones. Our experiments indicate that our system yields similar results to its non-private counterpart on standard multi-document evaluation datasets.

cs.IR↗

arXiv2015

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition

Most state-of-the-art action feature extractors involve differential operators, which act as highpass filters and tend to attenuate low frequency action information. This attenuation introduces bias to the resulting features and generates ill-conditioned feature matrices. The Gaussian Pyramid has been used as a feature enhancing technique that encodes scale-invariant characteristics into the feature space in an attempt to deal with this attenuation. However, at the core of the Gaussian Pyramid is a convolutional smoothing operation, which makes it incapable of generating new features at coarse scales. In order to address this problem, we propose a novel feature enhancing technique called Multi-skIp Feature Stacking (MIFS), which stacks features extracted using a family of differential filters parameterized with multiple time skips and encodes shift-invariance into the frequency space. MIFS compensates for information lost from using differential operators by recapturing information at coarse scales. This recaptured information allows us to match actions at different speeds and ranges of motion. We prove that MIFS enhances the learnability of differential-based features exponentially. The resulting feature matrices from MIFS have much smaller conditional numbers and variances than those from conventional methods. Experimental results show significantly improved performance on challenging action recognition and event detection tasks. Specifically, our method exceeds the state-of-the-arts on Hollywood2, UCF101 and UCF50 datasets and is comparable to state-of-the-arts on HMDB51 and Olympics Sports datasets. MIFS can also be used as a speedup strategy for feature extraction with minimal or no accuracy cost.

cs.CV↗

arXiv2015

Plagiarism Detection in Polyphonic Music using Monaural Signal Separation

Given the large number of new musical tracks released each year, automated approaches to plagiarism detection are essential to help us track potential violations of copyright. Most current approaches to plagiarism detection are based on musical similarity measures, which typically ignore the issue of polyphony in music. We present a novel feature space for audio derived from compositional modelling techniques, commonly used in signal separation, that provides a mechanism to account for polyphony without incurring an inordinate amount of computational overhead. We employ this feature representation in conjunction with traditional audio feature representations in a classification framework which uses an ensemble of distance features to characterize pairs of songs as being plagiarized or not. Our experiments on a database of about 3000 musical track pairs show that the new feature space characterization produces significant improvements over standard baselines.

cs.SD↗

arXiv2015

Unsupervised Fusion Weight Learning in Multiple Classifier Systems

In this paper we present an unsupervised method to learn the weights with which the scores of multiple classifiers must be combined in classifier fusion settings. We also introduce a novel metric for ranking instances based on an index which depends upon the rank of weighted scores of test points among the weighted scores of training points. We show that the optimized index can be used for computing measures such as average precision. Unlike most classifier fusion methods where a single weight is learned to weigh all examples our method learns instance-specific weights. The problem is formulated as learning the weight which maximizes a clarity index; subsequently the index itself and the learned weights both are used separately to rank all the test points. Our method gives an unsupervised method of optimizing performance on actual test data, unlike the well known stacking-based methods where optimization is done over a labeled training set. Moreover, we show that our method is tolerant to noisy classifiers and can be used for selecting N-best classifiers.

cs.LG↗

arXiv2014

Privacy-Preserving Important Passage Retrieval

State-of-the-art important passage retrieval methods obtain very good results, but do not take into account privacy issues. In this paper, we present a privacy preserving method that relies on creating secure representations of documents. Our approach allows for third parties to retrieve important passages from documents without learning anything regarding their content. We use a hashing scheme known as Secure Binary Embeddings to convert a key phrase and bag-of-words representation to bit strings in a way that allows the computation of approximate distances, instead of exact ones. Experiments show that our secure system yield similar results to its non-private counterpart on both clean text and noisy speech recognized text.

cs.IR↗

arXiv2013

Robust 1-bit Compressive Sensing via Gradient Support Pursuit

This paper studies a formulation of 1-bit Compressed Sensing (CS) problem based on the maximum likelihood estimation framework. In order to solve the problem we apply the recently proposed Gradient Support Pursuit algorithm, with a minor modification. Assuming the proposed objective function has a Stable Restricted Hessian, the algorithm is shown to accurately solve the 1-bit CS problem. Furthermore, the algorithm is compared to the state-of-the-art 1-bit CS algorithms through numerical simulations. The results suggest that the proposed method is robust to noise and at mid to low input SNR regime it achieves the best reconstruction SNR vs. execution time trade-off.

cs.IT↗