相关论文: Full-band General Audio Synthesis with Score-based…
Generative modeling offers new opportunities for bioacoustics, enabling the synthesis of realistic animal vocalizations that could support biomonitoring efforts and supplement scarce data for endangered species. However, directly generating…
Diffusion-based generative models have significantly advanced text-to-image synthesis, demonstrating impressive text comprehension and zero-shot generalization. These models refine images from random noise based on textual prompts, with…
Diffusion models have achieved state-of-the-art results in generative modelling but remain computationally intensive at inference time, often requiring thousands of discretization steps. To this end, we propose Sig-DEG (Signature-based…
Recent advances in generative models have made it possible to create high-quality, coherent music, with some systems delivering production-level output. Yet, most existing models focus solely on generating music from scratch, limiting their…
In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve…
Digital art synthesis is receiving increasing attention in the multimedia community because of engaging the public with art effectively. Current digital art synthesis methods usually use single-modality inputs as guidance, thereby limiting…
Medical image data is less accessible than in other domains due to privacy and regulatory constraints. In addition, labeling requires costly, time-intensive manual image annotation by clinical experts. To overcome these challenges,…
Diffusion and flow-matching models have revolutionized automatic text-to-audio generation in recent times. These models are increasingly capable of generating high quality and faithful audio outputs capturing to speech and acoustic events.…
Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the…
Unsupervised Anomalous Sound Detection (ASD) aims to design a generalizable method that can be used to detect anomalies when only normal sounds are given. In this paper, Anomalous Sound Detection based on Diffusion Models (ASD-Diffusion) is…
Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level observations such as image pixels. A prevailing line of research…
Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a…
Diffusion has emerged as a powerful framework for generative modeling, achieving remarkable success in applications such as image and audio synthesis. Enlightened by this progress, we propose a novel diffusion-based approach for symbolic…
Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative…
Although auto-regressive models excel in natural language processing, they often struggle to generate diverse text and provide limited controllability. Non-auto-regressive methods could be an alternative but often produce degenerate outputs…
We propose Polyffusion, a diffusion model that generates polyphonic music scores by regarding music as image-like piano roll representations. The model is capable of controllable music generation with two paradigms: internal control and…
Domain generalization (DG) for object detection aims to enhance detectors' performance in unseen scenarios. This task remains challenging due to complex variations in real-world applications. Recently, diffusion models have demonstrated…
In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements…
Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…
In this work, we propose an approach to music source separation that uses a generative diffusion model as a last-stage refinement on top of a deterministic separator, progressively enhancing the separated sources through iterative…