相关论文: TISDiSS: A Training-Time and Inference-Time Scalab…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression…

Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures…

We propose a block-online algorithm of guided source separation (GSS). GSS is a speech separation method that uses diarization information to update parameters of the generative model of observation signals. Previous studies have shown that…

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data…

The advancement of Time Series Foundation Models (TSFMs) has been driven primarily by large-scale pre-training, but inference-time compute potential remains largely untapped. This work systematically investigates two questions: how do TSFMs…

We propose a plug-and-play framework for speech enhancement and separation that augments predictive methods with a generative speech prior. Our approach, termed Stochastic Interpolant Prior for Speech (SIPS), builds on stochastic…

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper…

Diffusion models have recently advanced photorealistic human synthesis, although practical talking-head generation (THG) remains constrained by high inference latency, temporal instability such as flicker and identity drift, and imperfect…

Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to…

We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose frame-work for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize…

In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is…

This paper examines the implications of using the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) as both evaluation and training objective in supervised speech separation, when the training references contain noise, as is the case with…

This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep…

We present a novel approach that improves the performance of reverberant speech separation. Our approach is based on an accurate geometric acoustic simulator (GAS) which generates realistic room impulse responses (RIRs) by modeling both…

Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the difficulty in jointly…

Traditional source separation approaches train deep neural network models end-to-end with all the data available at once by minimizing the empirical risk on the whole training set. On the inference side, after training the model, the user…

A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…