Search Results for author:
Found 31 papers, 9 papers with code
AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR
Developing code-switched ASR systems is challenging due to language ambiguity and limited exposure to multilingual, code-switched data, while collecting such speech is costly.
Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment
This paper presents a novel non-invasive object classification approach using acoustic scattering, demonstrated through a case study on hair assessment.
Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages
Code-switching (CS), common in multilingual settings, presents challenges for ASR due to scarce and costly transcribed data caused by linguistic complexity.
Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
This paper presents our system for the MLC-SLM Challenge 2025, focusing on multilingual speech recognition and language modeling with large language models (LLMs).
CAMME: Adaptive Deepfake Image Detection with Multi-Modal Cross-Attention
The proliferation of sophisticated AI-generated deepfakes poses critical challenges for digital media authentication and societal security.
Communication Optimization for Decentralized Learning atop Bandwidth-limited Edge Networks
Decentralized federated learning (DFL) is a promising machine learning paradigm for bringing artificial intelligence (AI) capabilities to the network edge.
RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval
Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content.
Exploring ASR-Based Wav2Vec2 for Automated Speech Disorder Assessment: Insights and Analysis
With the rise of SSL and ASR technologies, the Wav2Vec2 ASR-based model has been fine-tuned for automated speech disorder quality assessment tasks, yielding impressive results and setting a new baseline for Head and Neck Cancer speech contexts.
Connective Viewpoints of Signal-to-Noise Diffusion Models
Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation.
Active Learning for WBAN-based Health Monitoring
These challenges make our problem fundamentally different from classical active learning, where unlabeled samples are free and labels can be queried in real time.
Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
While our focus is on empirical analysis, we believe it can guide backdoor research toward more realistic settings, highlighting the crucial role of FL in building robust defenses against diverse backdoor threats.
Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection
Recent synthetic speech detectors leveraging the Transformer model have superior performance compared to the convolutional neural network counterparts.
Ranked #4 on
Audio Deepfake Detection
on ASVspoof 2021
Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment
We achieve this for the LLaMA-2 7B model by combining the SparseGPT one-shot pruning method and sparse pretraining of those models on a subset of the SlimPajama dataset mixed with a Python subset of The Stack dataset.
Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context
Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation.
A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation
Additionally, we propose minimizing class-aware Higher-order Moment Matching (HMM) to align the corresponding class regions on the source and target domains.
Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training
Federated Recommendation (FedRec) systems have emerged as a solution to safeguard users' data in response to growing regulatory concerns.
DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition
The task of Visual Relationship Recognition (VRR) aims to identify relationships between two interacting objects in an image and is particularly challenging due to the widely-spread and highly imbalanced distribution of <subject, relation, object> triplets.
Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning
To address this, we propose the Gradient Projection Class-Prototype Conditional Diffusion Model (GPPDM), a GR-based approach for continual learning that enhances image quality in generators and thus reduces the CF in classifiers.
From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
We propose the Kuramoto Graph Neural Network (KuramotoGNN), a novel class of continuous-depth graph neural networks (GNNs) that employs the Kuramoto model to mitigate the over-smoothing phenomenon, in which node features in GNNs become indistinguishable as the number of layers increases.
p-Laplacian Transformer
$p$-Laplacian regularization, rooted in graph and image signal processing, introduces a parameter $p$ to control the regularization effect on these data.
Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy.
Federated Learning for ASR based on Wav2vec 2.0
This paper presents a study on the use of federated learning to train an ASR model based on a wav2vec 2. 0 model pre-trained by self supervision.
Sparse*BERT: Sparse Models Generalize To New tasks and Domains
Our experimentation shows that models that are pruned during pretraining using general domain masked language models can transfer to novel domains and tasks without extensive hyperparameter exploration or specialized approaches.
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models
We perform an in-depth study of the accuracy-compression trade-off for unstructured weight pruning of BERT models.
On Label Shift in Domain Adaptation via Wasserstein Distance
We study the label shift problem between the source and target domains in general domain adaptation (DA) settings.
SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation
Both automatic and human evaluation demonstrated that our approach can generate poems that have better cohesion without losing the quality due to additional loss.
STEM: An Approach to Multi-Source Domain Adaptation With Guarantees
To address the second challenge, we propose to bridge the gap between the target domain and the mixture of source domains in the latent space via a generator or feature extractor.
MOST: Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning
To this end, we propose in this paper a novel model for multi-source DA using the theory of optimal transport and imitation learning.
Imitation Learning
Multi-Source Unsupervised Domain Adaptation
+1
STEM: An Approach to Multi-Source Domain Adaptation With Guarantees
To address the second challenge, we propose to bridge the gap between the target domain and the mixture of source domains in the latent space via a generator or feature extractor.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Maximal Divergence Sequential Autoencoder for Binary Software Vulnerability Detection
Due to the sharp increase in the severity of the threat imposed by software vulnerabilities, the detection of vulnerabilities in binary code has become an important concern in the software industry, such as the embedded systems industry, and in the field of computer security.
Small Target Detection for Search and Rescue Operations using Distributed Deep Learning and Synthetic Data Generation
We compared the performance between the auto-detection system and the human eye.
