Towards Universal Mono-to-Binaural Speech Synthesis

15 Sept 2024 (modified: 26 Nov 2024)ICLR 2025 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Binaural audio, sound spatialization, neural sound synthesis, binaural speech
Abstract:

We consider the problem of synthesis of binaural speech from mono audio in arbitrary environments, which is important for modern telepresence and extended-reality applications. We find that existing neural mono-to-binaural methods are overfit to non-spatial acoustic properties, via analysis using a new benchmark (TUT Mono-to-Binaural), the first introduced since the original dataset of Richard et al. (2021). While these past methods focus on learning neural geometric transforms of monaural audio, we propose BinauralZero, a strong initial baseline for universal mono-to-binaural synthesis, which can subjectively match or outperform existing state-of-the-art neural mono-to-binaural renderers trained in their target environment despite never seeing any binaural data. It leverages the surprising discovery that an off-the-shelf mono audio denoising model can competently enhance the initial binauralization given by simple parameter-free transforms. We perform comprehensive ablations to understand how BinauralZero bridges the representation gap between mono and binaural audio, and analyze how current mono-to-binaural automated metrics are decorrelated from human ratings.

Supplementary Material: zip
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 888
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview