arXiv subjects

Bhiksha Raj

Publications and source records attributed to Bhiksha Raj.

At least 163 records · Page 9Linked to original sources

arXiv2021

Improving weakly supervised sound event detection with self-supervised auxiliary tasks

While multitask and transfer learning has shown to improve the performance of neural networks in limited data settings, they require pretraining of the model on large datasets beforehand. In this paper, we focus on improving the performance of weakly supervised sound event detection in low data and noisy settings simultaneously without requiring any pretraining task. To that extent, we propose a shared encoder architecture with sound event detection as a primary task and an additional secondary decoder for a self-supervised auxiliary task. We empirically evaluate the proposed framework for weakly supervised sound event detection on a remix dataset of the DCASE 2019 task 1 acoustic scene data with DCASE 2018 Task 2 sounds event data under 0, 10 and 20 dB SNR. To ensure we retain the localisation information of multiple sound events, we propose a two-step attention pooling mechanism that provides a time-frequency localisation of multiple audio events in the clip. The proposed framework with two-step attention outperforms existing benchmark models by 22.3%, 12.8%, 5.9% on 0, 10 and 20 dB SNR respectively. We carry out an ablation study to determine the contribution of the auxiliary task and two-step attention pooling to the SED performance improvement.

eess.AS↗

arXiv2021

Training image classifiers using Semi-Weak Label Data

In Multiple Instance learning (MIL), weak labels are provided at the bag level with only presence/absence information known. However, there is a considerable gap in performance in comparison to a fully supervised model, limiting the practical applicability of MIL approaches. Thus, this paper introduces a novel semi-weak label learning paradigm as a middle ground to mitigate the problem. We define semi-weak label data as data where we know the presence or absence of a given class and the exact count of each class as opposed to knowing the label proportions. We then propose a two-stage framework to address the problem of learning from semi-weak labels. It leverages the fact that counting information is non-negative and discrete. Experiments are conducted on generated samples from CIFAR-10. We compare our model with a fully-supervised setting baseline, a weakly-supervised setting baseline and learning from pro-portion (LLP) baseline. Our framework not only outperforms both baseline models for MIL-based weakly super-vised setting and learning from proportion setting, but also gives comparable results compared to the fully supervised model. Further, we conduct thorough ablation studies to analyze across datasets and variation with batch size, losses architectural changes, bag size and regularization

cs.LG↗

arXiv2021

FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances

Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification. In this work, we propose a white-box steganography-inspired adversarial attack that generates imperceptible adversarial perturbations against a speaker identification model. Our approach, FoolHD, uses a Gated Convolutional Autoencoder that operates in the DCT domain and is trained with a multi-objective loss function, in order to generate and conceal the adversarial perturbation within the original audio files. In addition to hindering speaker identification performance, this multi-objective loss accounts for human perception through a frame-wise cosine similarity between MFCC feature vectors extracted from the original and adversarial audio files. We validate the effectiveness of FoolHD with a 250-speaker identification x-vector network, trained using VoxCeleb, in terms of accuracy, success rate, and imperceptibility. Our results show that FoolHD generates highly imperceptible adversarial audio files (average PESQ scores above 4.30), while achieving a success rate of 99.6% and 99.2% in misleading the speaker identification model, for untargeted and targeted settings, respectively.

cs.SD↗

arXiv2020

Detection and Evaluation of human and machine generated speech in spoofing attacks on automatic speaker verification systems

Automatic speaker verification (ASV) systems utilize the biometric information in human speech to verify the speaker's identity. The techniques used for performing speaker verification are often vulnerable to malicious attacks that attempt to induce the ASV system to return wrong results, allowing an impostor to bypass the system and gain access. Attackers use a multitude of spoofing techniques for this, such as voice conversion, audio replay, speech synthesis, etc. In recent years, easily available tools to generate deepfaked audio have increased the potential threat to ASV systems. In this paper, we compare the potential of human impersonation (voice disguise) based attacks with attacks based on machine-generated speech, on black-box and white-box ASV systems. We also study countermeasures by using features that capture the unique aspects of human speech production, under the hypothesis that machines cannot emulate many of the fine-level intricacies of the human speech production mechanism. We show that fundamental frequency sequence-related entropy, spectral envelope, and aperiodic parameters are promising candidates for robust detection of deepfaked speech generated by unknown methods.

cs.SD↗

arXiv2020

Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection

Weakly Labelled learning has garnered lot of attention in recent years due to its potential to scale Sound Event Detection (SED) and is formulated as Multiple Instance Learning (MIL) problem. This paper proposes a Multi-Task Learning (MTL) framework for learning from Weakly Labelled Audio data which encompasses the traditional MIL setup. To show the utility of proposed framework, we use the input TimeFrequency representation (T-F) reconstruction as the auxiliary task. We show that the chosen auxiliary task de-noises internal T-F representation and improves SED performance under noisy recordings. Our second contribution is introducing two step Attention Pooling mechanism. By having 2-steps in attention mechanism, the network retains better T-F level information without compromising SED performance. The visualisation of first step and second step attention weights helps in localising the audio-event in T-F domain. For evaluating the proposed framework, we remix the DCASE 2019 task 1 acoustic scene data with DCASE 2018 Task 2 sounds event data under 0, 10 and 20 db SNR resulting in a multi-class Weakly labelled SED problem. The proposed total framework outperforms existing benchmark models over all SNRs, specifically 22.3 %, 12.8 %, 5.9 % improvement over benchmark model on 0, 10 and 20 dB SNR respectively. We carry out ablation study to determine the contribution of each auxiliary task and 2-step Attention Pooling to the SED performance improvement. The code is publicly released

eess.AS↗

arXiv2020

Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform (STFT) has been widely used for DNN-based speech enhancement over the last years, time domain methods such as the time-domain audio separation network (TasNet) have also been proposed. The most suitable method depends on the scale of the dataset and the type of task. In this paper, we explore the best speech enhancement algorithm on two different datasets. We propose a STFT-based method and a loss function using problem-agnostic speech encoder (PASE) features to improve subjective quality for the smaller dataset. Our proposed methods are effective on the Voice Bank + DEMAND dataset and compare favorably to other state-of-the-art methods. We also implement a low-latency version of TasNet, which we submitted to the DNS Challenge and made public by open-sourcing it. Our model achieves excellent performance on the DNS Challenge dataset.

eess.AS↗

arXiv2020

Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation

Although deep-learning-based methods have markedly improved the performance of speech separation over the past few years, it remains an open question how to integrate multi-channel signals for speech separation. We propose two methods, namely, early-fusion and late-fusion methods, to integrate multi-channel information based on the time-domain audio separation network, which has been proven effective in single-channel speech separation. We also propose channel-sequential-transfer learning, which is a transfer learning framework that applies the parameters trained for a lower-channel network as the initial values of a higher-channel network. For fair comparison, we evaluated our proposed methods using a spatialized version of the wsj0-2mix dataset, which is open-sourced. It was found that our proposed methods can outperform multi-channel deep clustering and improve the performance proportionally to the number of microphones. It was also proven that the performance of the late-fusion method is consistently higher than that of the single-channel method regardless of the angle difference between speakers.

eess.AS↗

arXiv2020

Exploring Optimal DNN Architecture for End-to-End Beamformers Based on Time-frequency References

Acoustic beamformers have been widely used to enhance audio signals. Currently, the best methods are the deep neural network (DNN)-powered variants of the generalized eigenvalue and minimum-variance distortionless response beamformers and the DNN-based filter-estimation methods that are used to directly compute beamforming filters. Both approaches are effective; however, they have blind spots in their generalizability. Therefore, we propose a novel approach for combining these two methods into a single framework that attempts to exploit the best features of both. The resulting model, called the W-Net beamformer, includes two components; the first computes time-frequency references that the second uses to estimate beamforming filters. The results on data that include a wide variety of room and noise conditions, including static and mobile noise sources, show that the proposed beamformer outperforms other methods on all tested evaluation metrics, which signifies that the proposed architecture allows for effective computation of the beamforming filters.

eess.AS↗

arXiv2020

Hide and Speak: Towards Deep Neural Networks for Speech Steganography

Steganography is the science of hiding a secret message within an ordinary public message, which is referred to as Carrier. Traditionally, digital signal processing techniques, such as least significant bit encoding, were used for hiding messages. In this paper, we explore the use of deep neural networks as steganographic functions for speech data. We showed that steganography models proposed for vision are less suitable for speech, and propose a new model that includes the short-time Fourier transform and inverse-short-time Fourier transform as differentiable layers within the network, thus imposing a vital constraint on the network outputs. We empirically demonstrated the effectiveness of the proposed method comparing to deep learning based on several speech datasets and analyzed the results quantitatively and qualitatively. Moreover, we showed that the proposed approach could be applied to conceal multiple messages in a single carrier using multiple decoders or a single conditional decoder. Lastly, we evaluated our model under different channel distortions. Qualitative experiments suggest that modifications to the carrier are unnoticeable by human listeners and that the decoded messages are highly intelligible.

cs.SD↗

arXiv2020

The phonetic bases of vocal expressed emotion: natural versus acted

Can vocal emotions be emulated? This question has been a recurrent concern of the speech community, and has also been vigorously investigated. It has been fueled further by its link to the issue of validity of acted emotion databases. Much of the speech and vocal emotion research has relied on acted emotion databases as valid proxies for studying natural emotions. To create models that generalize to natural settings, it is crucial to work with valid prototypes -- ones that can be assumed to reliably represent natural emotions. More concretely, it is important to study emulated emotions against natural emotions in terms of their physiological, and psychological concomitants. In this paper, we present an on-scale systematic study of the differences between natural and acted vocal emotions. We use a self-attention based emotion classification model to understand the phonetic bases of emotions by discovering the most 'attended' phonemes for each class of emotions. We then compare these attended-phonemes in their importance and distribution across acted and natural classes. Our tests show significant differences in the manner and choice of phonemes in acted and natural speech, concluding moderate to low validity and value in using acted speech databases for emotion classification tasks.

eess.AS↗

arXiv2020

Exploiting Non-Linear Redundancy for Neural Model Compression

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model compression techniques most of which rely on suboptimal heuristics and do not consider the parameter redundancies due to linear dependence between neuron activations in overparametrized networks. In this paper, we propose a novel model compression approach based on exploitation of linear dependence, that compresses networks by elimination of entire neurons and redistribution of their activations over other neurons in a manner that is provably lossless while training. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our method results in a reduction of up to 99\% in overall network size with small loss in performance. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with correct hyperparameter selection, our method is indeed able to capture and suppress those dependencies.

cs.LG↗

arXiv2020

W-Net BF: DNN-based Beamformer Using Joint Training Approach

Acoustic beamformers have been widely used to enhance audio signals. The best current methods are DNN-powered variants of the generalized eigenvalue beamformer, and DNN-based filterestimation methods that directly compute beamforming filters. Both approaches, while effective, have blindspots in their generalizability. We propose a novel approach that combines both approaches into a single framework that attempts to exploit the best features of both. The resulting model, called a W-Net beamformer, includes two components: the first computes a noise-masked reference which the second uses to estimate beamforming filters. Results on data that include a wide variety of room and noise conditions, including static and mobile noise sources, show that the proposed beamformer outperforms other methods in all tested evaluation metrics.

cs.SD↗

arXiv2019

Content-based Video Indexing and Retrieval Using Corr-LDA

Existing video indexing and retrieval methods on popular web-based multimedia sharing websites are based on user-provided sparse tagging. This paper proposes a very specific way of searching for video clips, based on the content of the video. We present our work on Content-based Video Indexing and Retrieval using the Correspondence-Latent Dirichlet Allocation (corr-LDA) probabilistic framework. This is a model that provides for auto-annotation of videos in a database with textual descriptors, and brings the added benefit of utilizing the semantic relations between the content of the video and text. We use the concept-level matching provided by corr-LDA to build correspondences between text and multimedia, with the objective of retrieving content with increased accuracy. In our experiments, we employ only the audio components of the individual recordings and compare our results with an SVM-based approach.

cs.IR↗

arXiv2019

Higher-order Network for Action Recognition

Capturing spatiotemporal dynamics is an essential topic in video recognition. In this paper, we present learnable higher-order operations as a generic family of building blocks for capturing spatiotemporal dynamics from RGB input video space. Similar to higher-order functions, the weights of higher-order operations are themselves derived from the data with learnable parameters. Classical architectures such as residual learning and network-in-network are first-order operations where weights are directly learned from the data. Higher-order operations make it easier to capture context-sensitive patterns, such as motion. Self-attention models are also higher-order operations, but the attention weights are mostly computed from an affine operation or dot product. Learnable higher-order operations can be more generic and flexible. Experimentally, we show that on the task of video recognition, our higher-order models can achieve results on par with or better than the existing state-of-the-art methods on Something-Something (V1 and V2), Kinetics and Charades datasets.

cs.CV↗

arXiv2019

Detecting gender differences in perception of emotion in crowdsourced data

Do men and women perceive emotions differently? Popular convictions place women as more emotionally perceptive than men. Empirical findings, however, remain inconclusive. Most prior studies focus on visual modalities. In addition, almost all of the studies are limited to experiments within controlled environments. Generalizability and scalability of these studies has not been sufficiently established. In this paper, we study the differences in perception of emotion between genders from speech data in the wild, annotated through crowdsourcing. While we limit ourselves to a single modality (i.e. speech), our framework is applicable to studies of emotion perception from all such loosely annotated data in general. Our paper addresses multiple serious challenges related to making statistically viable conclusions from crowdsourced data. Overall, the contributions of this paper are two fold: a reliable novel framework for perceptual studies from crowdsourced data; and the demonstration of statistically significant differences in speech-based emotion perception between genders.

cs.CL↗

arXiv2019

Learning Sound Events From Webly Labeled Data

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether from the learning process. We first develop a method of obtaining labeled audio data from the web (albeit noisy), in which no manual labeling is involved. We then describe methods to efficiently learn from these webly labeled audio recordings. In our proposed system, WeblyNet, two deep neural networks co-teach each other to robustly learn from webly labeled data, leading to around 17% relative improvement over the baseline method. The method also involves transfer learning to obtain efficient representations

cs.SD↗

arXiv2019

Reconstructing faces from voices

Voice profiling aims at inferring various human parameters from their speech, e.g. gender, age, etc. In this paper, we address the challenge posed by a subtask of voice profiling - reconstructing someone's face from their voice. The task is designed to answer the question: given an audio clip spoken by an unseen person, can we picture a face that has as many common elements, or associations as possible with the speaker, in terms of identity? To address this problem, we propose a simple but effective computational framework based on generative adversarial networks (GANs). The network learns to generate faces from voices by matching the identities of generated faces to those of the speakers, on a training set. We evaluate the performance of the network by leveraging a closely related task - cross-modal matching. The results show that our model is able to generate faces that match several biometric characteristics of the speaker, and results in matching accuracies that are much better than chance.

cs.SD↗

arXiv2019

Non-Determinism in Neural Networks for Adversarial Robustness

Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other areas. In most instances where these tasks are deployed in real-world scenarios, the models used in them have been shown to be susceptible to adversarial attacks, making it imperative for us to address the challenge of their adversarial robustness. Existing techniques for adversarial robustness fall into three broad categories: defensive distillation techniques, adversarial training techniques, and randomized or non-deterministic model based techniques. In this paper, we propose a novel neural network paradigm that falls under the category of randomized models for adversarial robustness, but differs from all existing techniques under this category in that it models each parameter of the network as a statistical distribution with learnable parameters. We show experimentally that this framework is highly robust to a variety of white-box and black-box adversarial attacks, while preserving the task-specific performance of the traditional neural network model.

cs.LG↗