Related papers: Compression of Acoustic Event Detection Models wit…

Model compression methods are used to reduce the computation and energy requirements for Large Language Models (LLMs). Quantization Aware Training (QAT), an effective model compression method, is proposed to reduce performance degradation…

Compressed sensing of simultaneously sparse and low-rank matrices enables recovery of sparse signals from a few linear measurements of their bilinear form. One important question is how many measurements are needed for a stable…

Compression of a neural network can help in speeding up both the training and the inference of the network. In this research, we study applying compression using low rank decomposition on network layers. Our research demonstrates that to…

While post-training model compression can greatly reduce the inference cost of a deep neural network, uncompressed training still consumes a huge amount of hardware resources, run-time and energy. It is highly desirable to directly train a…

Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of…

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.…

Considering that acoustic scenes and sound events are closely related to each other, in some previous papers, a joint analysis of acoustic scenes and sound events utilizing multitask learning (MTL)-based neural networks was proposed. In…

Sound event detection (SED) aims to detect when and recognize what sound events happen in an audio clip. Many supervised SED algorithms rely on strongly labelled data which contains the onset and offset annotations of sound events. However,…

Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly…

Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…

Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector…

The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel…

The deep neural network (DNN) based speech enhancement approaches have achieved promising performance. However, the number of parameters involved in these methods is usually enormous for the real applications of speech enhancement on the…

Modern electron tomography has progressed to higher resolution at lower doses by leveraging compressed sensing methods that minimize total variation (TV). However, these sparsity-emphasized reconstruction algorithms introduce tunable…

Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling. However, it is a very challenging problem when the image data contains significant occlusion, noise, illumination variation, and…

We propose a compression based continual task learning method that can dynamically grow a neural network. Inspired from the recent model compression techniques, we employ compression-aware training and perform low-rank weight approximations…

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from…

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress…

Designing neural architectures is a fundamental step in deep learning applications. As a partner technique, model compression on neural networks has been widely investigated to gear the needs that the deep learning algorithms could be run…

Subspace segmentation assumes that data comes from the union of different subspaces and the purpose of segmentation is to partition the data into the corresponding subspace. Low-rank representation (LRR) is a classic spectral-type method…