ComplexDec：一种具有复数频谱建模的领域鲁棒高保真神经音频编解码器
ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling
AI总结：
本文提出48 kHz全频带神经音频编解码器ComplexDec，通过复数频谱建模缓解压缩信息损失，在24 kbps比特率下仅用30小时VCTK数据训练即实现领域外鲁棒性。
摘要：
神经音频编解码器已在音频生成任务中被广泛采用，因为其紧凑且离散的表示既适用于大语言模型风格的生成模型，也适用于基于回归的生成模型。然而，大多数神经编解码器难以对领域外音频进行建模，从而导致误差传播到下游生成任务。在本文中，我们首先论证编解码器压缩造成的信息损失会降低领域外鲁棒性。然后，我们提出全频带48 kHz的ComplexDec，其采用复数频谱输入和输出以缓解信息损失，同时采用与基线AuidoDec和ScoreDec相同的24 kbps比特率。客观和主观评估表明，仅使用30小时VCTK语料库训练的ComplexDec具有领域外鲁棒性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
