BNMusic: Blending Environmental Noises into Personalized Music
Chi Zuo, Martin B. M{\o}ller, Pablo Mart\'inez-Nuevo, Huayang Huang, Yu Wu, Ye Zhu

TL;DR
BNMusic introduces a novel approach to reduce environmental noise annoyance by blending noises into personalized music generated from text prompts, improving acoustic experience without excessive volume increases.
Contribution
The paper presents a two-stage framework for blending environmental noises into personalized music using mel-spectrogram synthesis and adaptive amplification, advancing noise masking techniques.
Findings
Effective noise blending demonstrated on multiple datasets
Reduces noise noticeability while maintaining music quality
Enhances user experience in noisy environments
Abstract
While being disturbed by environmental noises, the acoustic masking technique is a conventional way to reduce the annoyance in audio engineering that seeks to cover up the noises with other dominant yet less intrusive sounds. However, misalignment between the dominant sound and the noise-such as mismatched downbeats-often requires an excessive volume increase to achieve effective masking. Motivated by recent advances in cross-modal generation, in this work, we introduce an alternative method to acoustic masking, aiming to reduce the noticeability of environmental noises by blending them into personalized music generated based on user-provided text prompts. Following the paradigm of music generation using mel-spectrogram representations, we propose a Blending Noises into Personalized Music (BNMusic) framework with two key stages. The first stage synthesizes a complete piece of music in a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsMusic and Audio Processing · Music Technology and Sound Studies · Generative Adversarial Networks and Image Synthesis
