Self-supervised visual acoustic matching

A Somayazulu, C Chen… - Advances in Neural …, 2024‏ - proceedings.neurips.cc
Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a
target acoustic environment. Existing methods assume access to paired training data, where …

Visual acoustic matching

C Chen, R Gao, P Calamia… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
We introduce the visual acoustic matching task, in which an audio clip is transformed to
sound like it was recorded in a target environment. Given an image of the target environment …

Novel-view acoustic synthesis

C Chen, A Richard, R Shapovalov… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
We introduce the novel-view acoustic synthesis (NVAS) task: given the sight and sound
observed at a source viewpoint, can we synthesize the sound of that scene from an unseen …

Rendering spatial sound for interoperable experiences in the audio metaverse

JM Jot, R Audfray, M Hertensteiner… - 2021 Immersive and …, 2021‏ - ieeexplore.ieee.org
Interactive audio spatialization technology previously developed for video game authoring
and rendering has evolved into an essential component of platforms enabling shared …

Mixed reality spatial audio

BL Schmidt, J Tajik, JM Jot - US Patent 10,616,705, 2020‏ - Google Patents
(57) ABSTRACT A method of presenting an audio signal to a user of a mixed reality
environment is disclosed. According to examples of the method, an audio event associated …

Vit-tts: visual text-to-speech with scalable diffusion transformer

H Liu, R Huang, X Lin, W Xu, M Zheng, H Chen… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Text-to-speech (TTS) has undergone remarkable improvements in performance, particularly
with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the …

Blind room volume estimation from single-channel noisy speech

AF Genovese, H Gamper, V Pulkki… - ICASSP 2019-2019 …, 2019‏ - ieeexplore.ieee.org
Recent work on acoustic parameter estimation indicates that geometric room volume can be
useful for modeling the character of an acoustic environment. However, estimating volume …

Blind acoustic room parameter estimation using phase features

C Ick, A Mehrabi, W ** - ICASSP 2023-2023 IEEE International …, 2023‏ - ieeexplore.ieee.org
Modeling room acoustics in a real-world settings involves some degree of blind parameter
estimation from noisy and reverberant audio. Modern approaches leverage convolutional …

Audio splicing detection using convolutional neural network

S Jadhav, R Patole, P Rege - 2019 10th International …, 2019‏ - ieeexplore.ieee.org
In an audio forensics scenario includes audio authentication in which major investigation
topic is audio tampering detection. In this paper, we present a novel method of splicing …

Mutual learning for acoustic matching and dereverberation via visual scene-driven diffusion

J Ma, W Wang, Y Yang, F Zheng - European Conference on Computer …, 2024‏ - Springer
Visual acoustic matching (VAM) is pivotal for enhancing the immersive experience, and the
task of dereverberation is effective in improving audio intelligibility. Existing methods treat …