ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling
Year: 2025
Type: conference-paper
Abstract: Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48 kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24 kbps bitrate as the baseline AuidoDec and ScoreDec. Objective and subjective evaluations demonstrate the out-of-domain robustness of ComplexDec trained using only the 30-hour VCTK corpus.
Authors: Yi-Chiao Wu, Dejan Marković, Steven Krenn, Israel D. Gebru, Alexander Richard
Institution: Meta (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4408353007