相关论文: Few-shot Acoustic Synthesis with Multimodal Flow M…

Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using…

Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of…

Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time…

Despite recent advances in text-to-speech (TTS) models, audio-visual-to-audio-visual (AV2AV) translation still faces a critical challenge: maintaining speaker consistency between the original and translated vocal and facial features. To…

We address the challenge of detecting synthesized speech under distribution shifts -- arising from unseen synthesis methods, speakers, languages, or audio conditions -- relative to the training data. Few-shot learning methods are a…

The acoustic space in which a sound is created and heard plays an essential role in how that sound is perceived by affording a unique sense of \textit{presence}. Every sound we hear results from successive convolution operations intrinsic…

Zero-shot voice conversion (VC) aims to transfer timbre from a source speaker to any unseen target speaker while preserving linguistic content. Growing application scenarios demand models with streaming inference capabilities. This has…

Few-shot bioacoustic event detection consists in detecting sound events of specified types, in varying soundscapes, while having access to only a few examples of the class of interest. This task ran as part of the DCASE challenge for the…

Infrared (IR) imaging is commonly used in various scenarios, including autonomous driving, fire safety and defense applications. Thus, semantic segmentation of such images is of great interest. However, this task faces several challenges,…

Accurate and real-time radio map (RM) generation is crucial for next-generation wireless systems, yet diffusion-based approaches often suffer from large model sizes, slow iterative denoising, and high inference latency, which hinder…

Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and…

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel…

Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data while requiring models to acquire new knowledge without catastrophic forgetting. Recent works have explored generative models, particularly…

This work introduces an economic solution for the problems of sound insulation of recording studios. Sound insulation at wall resonance frequency is weak. Instead of acoustical treatment, a digital filter is used to eliminate the effects of…

Room Impulse Response (RIR) prediction at arbitrary receiver positions is essential for practical applications such as spatial audio rendering. We propose Neural Acoustic Multipole Splatting (NAMS), which synthesizes RIRs at unseen receiver…

Room Impulse Responses (RIRs) characterize acoustic environments and are crucial in multiple audio signal processing tasks. High-quality RIR estimates drive applications such as virtual microphones, sound source localization, augmented…

Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling, however, their potential for automatic speech recognition (ASR) remains largely unexplored. We propose Drax, a discrete flow…

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…

Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the…

This paper introduces FlowMAC, a novel neural audio codec for high-quality general audio compression at low bit rates based on conditional flow matching (CFM). FlowMAC jointly learns a mel spectrogram encoder, quantizer and decoder. At…