Related papers: Few-shot Acoustic Synthesis with Multimodal Flow M…

We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We consider two scenarios, viz.: (a) when a differentiable…

Existing generative retrieval (GR) methods rely on training-based indexing, which fine-tunes a model to memorise associations between queries and the document identifiers (docids) of relevant documents. Training-based indexing suffers from…

Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to…

The field of novel view synthesis from images has seen rapid advancements with the introduction of Neural Radiance Fields (NeRF) and more recently with 3D Gaussian Splatting. Gaussian Splatting became widely adopted due to its efficiency…

Few-shot class-incremental learning (FSCIL) poses significant challenges for artificial neural networks due to the need to efficiently learn from limited data while retaining knowledge of previously learned tasks. Inspired by the brain's…

Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear…

Text-to-image synthesis models require the ability to generate diverse images while maintaining stability. To overcome this challenge, a number of methods have been proposed, including the collection of prompt-image datasets and the…

Few-shot recognition (FSR) aims to train a classification model with only a few labeled examples of each concept concerned by a downstream task, where data annotation cost can be prohibitively high. We develop methods to solve FSR by…

Audio adversarial examples are audio files that have been manipulated to fool an automatic speech recognition (ASR) system, while still sounding benign to a human listener. Most methods to generate such samples are based on a two-step…

It is generally assumed that number of classes is fixed in current audio classification methods, and the model can recognize pregiven classes only. When new classes emerge, the model needs to be retrained with adequate samples of all…

Learning-based scene representations such as neural radiance fields or light field networks, that rely on fitting a scene model to image observations, commonly encounter challenges in the presence of inconsistencies within the images caused…

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook…

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the…

Recent advancements in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment. While recent methods…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…

Few-shot class-incremental learning (FSCIL) aims to learn sequential classes with limited samples in a few-shot fashion. Inherited from the classical class-incremental learning setting, the popular benchmark of FSCIL uses averaged accuracy…

This paper introduces a novel task in generative speech processing, Acoustic Scene Transfer (AST), which aims to transfer acoustic scenes of speech signals to diverse environments. AST promises an immersive experience in speech perception…

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Generative models, including diffusion and flow-based models, often exhibit systematic biases that degrade sample quality, particularly in high-dimensional settings. We revisit refinement methods and show that effective bias correction can…

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…