Related papers: Fully Few-shot Class-incremental Audio Classificat…

Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring…

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding…

Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These…

Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is largely caused by the lack of generalizability and…

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks.…

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

Few-shot class-incremental learning (FSCIL) presents the primary challenge of balancing underfitting to a new session's task and forgetting the tasks from previous sessions. To address this challenge, we develop a simple yet powerful…

Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio classification using automatically generated sound attribute…

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…

In this paper, we tackle the problem of handling narrowband and wideband speech by building a single acoustic model (AM), also called mixed bandwidth AM. In the proposed approach, an auxiliary input feature is used to provide the bandwidth…

We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical…

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…

We introduce Mixture-based Feature Space Learning (MixtFSL) for obtaining a rich and robust feature representation in the context of few-shot image classification. Previous works have proposed to model each base class either with a single…

In recent years, deep learning-based approaches have significantly improved the performance of single-channel speech enhancement. However, due to the limitation of training data and computational complexity, real-time enhancement of…

Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few-shot classification. Few-shot classification involves…

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality,…

In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. We perform an exploration into how a GAN can be fine-tuned for such a task (one of which is in a…

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled…

Effective image classification hinges on discerning relevant features from both foreground and background elements, with the foreground typically holding the critical information. While humans adeptly classify images with limited exposure,…