Related papers: LightSAFT: Lightweight Latent Source Aware Frequen…
Music source separation is the task of extracting an estimate of one or more isolated sources or instruments (for example, drums or vocals) from musical audio. The task of music demixing or unmixing considers the case where the musical…
Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…
Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…
Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs,…
BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is…
The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipelines. However, recent model designs for MSS were mainly…
Many applications of single channel source separation (SCSS) including automatic speech recognition (ASR), hearing aids etc. require an estimation of only one source from a mixture of many sources. Treating this special case as a regular…
Performance of cooperative diversity schemes at Low Signal to Noise Ratios (LSNR) was recently studied by Avestimehr et. al. [1] who emphasized the importance of diversity gain over multiplexing gain at low SNRs. It has also been pointed…
Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack…
Music source separation has been intensively studied in the last decade and tremendous progress with the advent of deep learning could be observed. Evaluation campaigns such as MIREX or SiSEC connected state-of-the-art models and…
Learning lighting adaptation is a crucial step in achieving good visual perception and supporting downstream vision tasks. Current research often addresses individual light-related challenges, such as high dynamic range imaging and exposure…
We present the source separation framework SCARLET for multi-band images, which is based on a generalization of the Non-negative Matrix Factorization to alternative and several simultaneous constraints. Our approach describes the observed…
Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we…
Federated Learning (FL) plays a critical role in distributed systems. In these systems, data privacy and confidentiality hold paramount importance, particularly within edge-based data processing systems such as IoT devices deployed in smart…
Most of the current supervised automatic music transcription (AMT) models lack the ability to generalize. This means that they have trouble transcribing real-world music recordings from diverse musical genres that are not presented in the…
This paper proposes methods that can optimize a Convolutional BeamFormer (CBF) for jointly performing denoising, dereverberation, and source separation (DN+DR+SS) in a computationally efficient way. Conventionally, cascade configuration…
In recent years, decentralized sensor networks have garnered significant attention in the field of state estimation owing to enhanced robustness, scalability, and fault tolerance. Optimal fusion performance can be achieved under fully…
End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct…
Recent approaches in source separation leverage semantic information about their input mixtures and constituent sources that when used in conditional separation models can achieve impressive performance. Most approaches along these lines…
Existing stereo matching networks typically rely on either cost-volume construction based on 3D convolutions or deformation methods based on iterative optimization. The former incurs significant computational overhead during cost…