Related papers: Music Boomerang: Reusing Diffusion Models for Data…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore the essential variety within a single sample using hard…

Diffusion-based generative models demonstrate state-of-the-art performance across various image synthesis tasks, yet their tendency to replicate and amplify dataset biases remains poorly understood. Although previous research has viewed…

Although recent speech processing technologies have achieved significant improvements in objective metrics, there still remains a gap in human perceptual quality. This paper proposes Diffiner, a novel solution that utilizes the powerful…

In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think…

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts…

Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear…

Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

We propose a timbre conversion model based on the Diffusion architecture de-signed to precisely translate music played by various instruments into piano ver-sions. The model employs a Pitch Encoder and Loudness Encoder to extract pitch and…

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer…

Singing voice synthesis (SVS) aims to generate expressive and high-quality vocals from musical scores, requiring precise modeling of pitch, duration, and articulation. While diffusion-based models have achieved remarkable success in image…

Data augmentation is a valuable tool for the design of deep learning systems to overcome data limitations and stabilize the training process. Especially in the medical domain, where the collection of large-scale data sets is challenging and…

Deep generative models produce data according to a learned representation, e.g. diffusion models, through a process of approximation computing possible samples. Approximation can be understood as reconstruction and the large datasets used…

Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…

Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…

The task of bandwidth extension addresses the generation of missing high frequencies of audio signals based on knowledge of the low-frequency part of the sound. This task applies to various problems, such as audio coding or audio…