相关论文: Room Impulse Response Generation Conditioned on Ac…

Discrete diffusion models generate sequences by iteratively denoising samples corrupted by categorical noise, offering an appealing alternative to autoregressive decoding for structured and symbolic generation. However, standard training…

A Recurrent Neural Network (RNN) for audio synthesis is trained by augmenting the audio input with information about signal characteristics such as pitch, amplitude, and instrument. The result after training is an audio synthesizer that is…

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular…

Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room…

In this work, we introduce a novel framework which combines physics and machine learning methods to analyse acoustic signals. Three methods are developed for this task: a Bayesian inference approach for inferring the spectral acoustics…

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their…

Predicting Room Impulse Responses (RIRs) remains a challenge due to the high dimensionality of audio signals and the need for perceptual accuracy. This paper introduces a neural network framework that predicts multi-band Energy Decay Curves…

We introduce a novel algorithm for online estimation of acoustic impulse responses (AIRs) which allows for fast convergence by exploiting prior knowledge about the fundamental structure of AIRs. The proposed method assumes that the…

Predicting spatially varying Room Impulse Response (RIR) from sparse observations is a critical but highly challenging inverse problem for immersive spatial audio rendering. In this work, we present EIGENET, a geometry-informed multi-modal…

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or…

The image-source method is widely applied to compute room impulse responses (RIRs) of shoebox rooms with arbitrary absorption. However, with increasing RIR lengths, the number of image sources grows rapidly, leading to slow computation. In…

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound…

Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…

Existing Reward Models (RMs), typically trained on general preference data, struggle in Retrieval Augmented Generation (RAG) settings, which require judging responses for faithfulness to retrieved context, relevance to the user query,…

Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Most GR methods follow a quantization-representation-generation pipeline, first…

Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward…

Reconfigurable intelligent surface (RIS) is a promising technique to enhance the performance of physical-layer key generation (PKG) due to its ability to smartly customize the radio environments. Existing RIS-assisted PKG methods are mainly…

Our everyday auditory experience is shaped by the acoustics of the indoor environments in which we live. Room acoustics modeling is aimed at establishing mathematical representations of acoustic wave propagation in such environments. These…

Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic methods like DDIM, the absence of time conditioning leads to…