Related papers: FLAMO: An Open-Source Library for Frequency-Domain…
Algorithm portfolio and selection approaches have achieved remarkable improvements over single solvers. However, the implementation of such systems is often highly customised and specific to the problem domain. This makes it difficult for…
This article presents new numerical simulation tools, respectively developed in Matlab and Blender softwares. Available in open-source under the GPL 3.0 license, it uses a ray-tracing/image-sources hybrid method to calculate the room…
Time-frequency (TF) representations in audio synthesis have been increasingly modeled with real-valued networks. However, overlooking the complex-valued nature of TF representations can result in suboptimal performance and require…
Modern computer systems are highly configurable, with hundreds of configuration options that interact, resulting in an enormous configuration space. As a result, optimizing performance goals (e.g., latency) in such systems is challenging…
The auto differentiable simulation is a type of simulation that outputs of the simulation include not only the simulation result itself, but also their derivatives with respect to various input parameters. It provides an efficient method to…
In a range of recent works, object-centric architectures have been shown to be suitable for unsupervised scene decomposition in the vision domain. Inspired by these methods we present AudioSlots, a slot-centric generative model for blind…
We present Vibrato Nonnegative Tensor Factorization, an algorithm for single-channel unsupervised audio source separation with an application to separating instrumental or vocal sources with nonstationary pitch from music recordings. Our…
This paper proposes a novel scheme for cell-free massive multiple-input multiple-output (CFmMIMO) networks to support any federated learning (FL) framework. This scheme allows each instead of all the iterations of the FL framework to happen…
Recent advances in large language models (LLMs) and audio language models have significantly improved music generation, particularly in lyrics-to-song generation. However, existing approaches still struggle with the complex composition of…
Audio Super-Resolution is a set of techniques aimed at high-quality estimation of the given signal as if it would be sampled with higher sample rate. Among suggested methods there are diffusion and flow models (which are considered slower),…
Neural networks have become ubiquitous in audio effects modelling, especially for guitar amplifiers and distortion pedals. One limitation of such models is that the sample rate of the training data is implicitly encoded in the model weights…
Recently, compositional optimization (CO) has gained popularity because of its applications in distributionally robust optimization (DRO) and many other machine learning problems. Large-scale and distributed availability of data demands the…
Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…
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…
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a…
Spherical microphone arrays (SMAs) and spherical loudspeaker arrays (SLAs) facilitate the study of room acoustics due to the three-dimensional analysis they provide. More recently, systems that combine both arrays, referred to as…
Reconstructing the sound field in a room is an important task for several applications, such as sound control and augmented (AR) or virtual reality (VR). In this paper, we propose a data-driven generative model for reconstructing the…
Instruction fine-tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying…
Federated Learning (FL) has recently emerged as a popular solution to distributedly train a model on user devices improving user privacy and system scalability. Major Internet companies have deployed FL in their applications for specific…
Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks that require structured…