Related papers: SepTr: Separable Transformer for Audio Spectrogram…

Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…

We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker…

Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length),…

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained…

Audio source separation is often achieved by estimating the magnitude spectrogram of each source, and then applying a phase recovery (or spectrogram inversion) algorithm to retrieve time-domain signals. Typically, spectrogram inversion is…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Spectrum multiplexer enables simultaneous transmission of multiple narrow-band IoT signals through gateway devices, thereby enhancing overall spectrum utilization. We propose a novel solution based on filter banks that offer increased…

We present a novel bi-directional Transformer architecture (BiXT) which scales linearly with input size in terms of computational cost and memory consumption, but does not suffer the drop in performance or limitation to only one input…

Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by…

Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \cite{dosovitskiy2020image}, DeIT, \cite{touvron2021training}) similar to the original work in…

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a…

We introduce the Block-Recurrent Transformer, which applies a transformer layer in a recurrent fashion along a sequence, and has linear complexity with respect to sequence length. Our recurrent cell operates on blocks of tokens rather than…

With the development of the convolutional neural network, image style transfer has drawn increasing attention. However, most existing approaches adopt a global feature transformation to transfer style patterns into content images (e.g.,…

The goal of the audio-visual segmentation (AVS) task is to segment the sounding objects in the video frames using audio cues. However, current fusion-based methods have the performance limitations due to the small receptive field of…

Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer…

Representation learning frameworks in unlabeled time series have been proposed for medical signal processing. Despite the numerous excellent progresses have been made in previous works, we observe the representation extracted for the time…

We present a spectrogram separation method tailored for mixtures comprising two nonstationary components. By exploiting the unique characteristics of their time-frequency representations, we propose an inverse problem formulation to…

Interactive segmentation aims to extract objects of interest from an image based on user-provided clicks. In real-world applications, there is often a need to segment a series of images featuring the same target object. However, existing…

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…