Lightweight Implicit Neural Network for Binaural Audio Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Xikun, Liu, Fang, Shi, Weizhi, Sang, Jinqiu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912842323591168
author Lu, Xikun
Liu, Fang
Shi, Weizhi
Sang, Jinqiu
author_facet Lu, Xikun
Liu, Fang
Shi, Weizhi
Sang, Jinqiu
contents High-fidelity binaural audio synthesis is crucial for immersive listening, but existing methods require extensive computational resources, limiting their edge-device application. To address this, we propose the Lightweight Implicit Neural Network (Lite-INN), a novel two-stage framework. Lite-INN first generates initial estimates using a time-domain warping, which is then refined by an Implicit Binaural Corrector (IBC) module. IBC is an implicit neural network that predicts amplitude and phase corrections directly, resulting in a highly compact model architecture. Experimental results show that Lite-INN achieves statistically comparable perceptual quality to the best-performing baseline model while significantly improving computational efficiency. Compared to the previous state-of-the-art method (NFS), Lite-INN achieves a 72.7% reduction in parameters and requires significantly fewer compute operations (MACs). This demonstrates that our approach effectively addresses the trade-off between synthesis quality and computational efficiency, providing a new solution for high-fidelity edge-device spatial audio applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14069
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lightweight Implicit Neural Network for Binaural Audio Synthesis
Lu, Xikun
Liu, Fang
Shi, Weizhi
Sang, Jinqiu
Audio and Speech Processing
Sound
High-fidelity binaural audio synthesis is crucial for immersive listening, but existing methods require extensive computational resources, limiting their edge-device application. To address this, we propose the Lightweight Implicit Neural Network (Lite-INN), a novel two-stage framework. Lite-INN first generates initial estimates using a time-domain warping, which is then refined by an Implicit Binaural Corrector (IBC) module. IBC is an implicit neural network that predicts amplitude and phase corrections directly, resulting in a highly compact model architecture. Experimental results show that Lite-INN achieves statistically comparable perceptual quality to the best-performing baseline model while significantly improving computational efficiency. Compared to the previous state-of-the-art method (NFS), Lite-INN achieves a 72.7% reduction in parameters and requires significantly fewer compute operations (MACs). This demonstrates that our approach effectively addresses the trade-off between synthesis quality and computational efficiency, providing a new solution for high-fidelity edge-device spatial audio applications.
title Lightweight Implicit Neural Network for Binaural Audio Synthesis
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2509.14069