Search Results for author:
Found 41 papers, 9 papers with code
Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection
The data produced using the framework serves as a benchmark for anomaly detection applications, potentially enhancing the performance of models trained on audio data, particularly in handling out-of-distribution cases.
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
Furthermore, we design three benchmark datasets focused on label noise detection, label noise learning, and class-imbalanced learning.
A Multi-Agent Reinforcement Learning Framework for Evaluating the U.S. Ending the HIV Epidemic Plan
Human immunodeficiency virus (HIV) is a major public health concern in the United States, with about 1. 2 million people living with HIV and 35, 000 newly infected each year.
Psychoacoustic Challenges Of Speech Enhancement On VoIP Platforms
Within the ambit of VoIP (Voice over Internet Protocol) telecommunications, the complexities introduced by acoustic transformations merit rigorous analysis.
LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model
We hypothesize that for attacks to be transferrable, it is sufficient if the proxy can approximate the target model in the neighborhood of the harmful query.
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks.
Online Active Learning For Sound Event Detection
Online Active Learning (OAL) is a paradigm that addresses this issue by simultaneously minimizing the amount of annotation required to train a classifier and adapting to changes in the data over the duration of the data collection process.
Importance of negative sampling in weak label learning
Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known.
Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents
Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during pretraining.
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations.
Ranked #1 on
Learning with noisy labels
on mini WebVision 1.0
Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation
The knowledge gained from our study on the adversary's ability to make specific evasive perturbations to different types of malicious packets can help defenders enhance the robustness of their NIDS against evolving adversarial attacks.
Improving Perceptual Quality, Intelligibility, and Acoustics on VoIP Platforms
In this paper, we present a method for fine-tuning models trained on the Deep Noise Suppression (DNS) 2020 Challenge to improve their performance on Voice over Internet Protocol (VoIP) applications.
Exploiting Contextual Structure to Generate Useful Auxiliary Tasks
We propose an approach that maximizes experience reuse while learning to solve a given task by generating and simultaneously learning useful auxiliary tasks.
Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Preliminary results show (1) the proposed BECR can incur a more dispersed embedding on the test set, (2) BECR improves the PaSST model without extra computation complexity, and (3) STFT preprocessing outperforms CQT in all tasks we tested.
Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments
We propose Lang2LTL, a modular system and a software package that leverages large language models (LLMs) to ground temporal navigational commands to LTL specifications in environments without prior language data.
Conformers are All You Need for Visual Speech Recognition
We achieve a new state-of-the-art of 12. 8% WER for visual speech recognition on the TED LRS3 dataset, which rivals the performance of audio-only models from just four years ago.
Ranked #1 on
Lipreading
on LRS3-TED
(using extra training data)
Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework
The current approaches are deterministic and one-time decision-making methods, which do not consider future uncertainties when prioritizing and selecting vulnerabilities for mitigation.
Automated Audio Captioning and Language-Based Audio Retrieval
This project involved participation in the DCASE 2022 Competition (Task 6) which had two subtasks: (1) Automated Audio Captioning and (2) Language-Based Audio Retrieval.
Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations
In this work, we identify the roots of this challenge as the failure of a learned continuous policy to satisfy the discrete plan implicit in the demonstration.
Financial Time Series Data Augmentation with Generative Adversarial Networks and Extended Intertemporal Return Plots
Data augmentation is a key regularization method to support the forecast and classification performance of highly parameterized models in computer vision.
On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice
Lately, there has been a global effort by multiple research groups to detect COVID-19 from voice.
Ontological Learning from Weak Labels
We find that the baseline Siamese does not perform better by incorporating ontology information in the weak and multi-label scenario, but that the GCN does capture the ontology knowledge better for weak, multi-labeled data.
An Overview of Techniques for Biomarker Discovery in Voice Signal
This paper reflects on the effect of several categories of medical conditions on human voice, focusing on those that may be hypothesized to have effects on voice, but for which the changes themselves may be subtle enough to have eluded observation in standard analytical examinations of the voice signal.
Supervised Bayesian Specification Inference from Demonstrations
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
Feature extraction and evaluation for BioMedical Question Answering
In this paper, we present our work on the BioASQ pipeline.
Training image classifiers using Semi-Weak Label Data
Thus, this paper introduces a novel semi-weak label learning paradigm as a middle ground to mitigate the problem.
A Reinforcement Learning Approach for Rebalancing Electric Vehicle Sharing Systems
This paper proposes a reinforcement learning approach for nightly offline rebalancing operations in free-floating electric vehicle sharing systems (FFEVSS).
Interactive Robot Training for Non-Markov Tasks
Defining sound and complete specifications for robots using formal languages is challenging, while learning formal specifications directly from demonstrations can lead to over-constrained task policies.
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example
To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx.
Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming.
Sound event detection in domestic environments withweakly labeled data and soundscape synthesis
This paper presents Task 4 of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and provides a first analysis of the challenge results.
Ranked #9 on
Sound Event Detection
on DESED
Bayesian Inference of Temporal Task Specifications from Demonstrations
When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task.
Learning Sound Events From Webly Labeled Data
In the last couple of years, weakly labeled learning for sound events has turned out to be an exciting approach for audio event detection.
Two Can Play That Game: An Adversarial Evaluation of a Cyber-alert Inspection System
In order to explain this observation, we extend the earlier RL model to a game model and show that there exists defender policies that can be robust against any adversarial policy.
CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
Our experiments indicate a considerable improvement in object detection accuracy: +8. 51% for CM and +6. 20% for ACM.
Natural Language Person Search Using Deep Reinforcement Learning
Deep Reinforcement learning with appropriate constraints would look only for the relevant person in the image as opposed to an unconstrained approach where each individual objects in the image are ranked.
Activity Recognition on a Large Scale in Short Videos - Moments in Time Dataset
Moments capture a huge part of our lives.
A Closer Look at Weak Label Learning for Audio Events
In this work, we first describe a CNN based approach for weakly supervised training of audio events.
NELS-Never-Ending Learner of Sounds
Sounds are essential to how humans perceive and interact with the world.
Framework for evaluation of sound event detection in web videos
The framework crawls videos using search queries corresponding to 78 sound event labels drawn from three datasets.
An Approach for Self-Training Audio Event Detectors Using Web Data
The audio event detectors are trained on the labeled audio and ran on the unlabeled audio downloaded from YouTube.
