EVA-GAN：通过可扩展生成对抗网络实现增强型多样化音频生成
EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks
AI总结：
针对音频生成领域规模化探索不足、现有模型难生成44.1kHz高保真音频且存在频谱不连续、高频模糊、域外鲁棒性差的问题，提出含2亿参数的EVA-GAN，结合大规模音频数据、上下文感知模块等人在环工具，显著提升重建效果与鲁棒性，支持高保真音频生成。
摘要：
大模型的出现标志着机器学习进入新纪元，它借助海量数据集捕捉并合成复杂模式，性能显著优于小型模型。尽管取得了这些进展，针对模型规模化的探索，尤其是在音频生成领域，仍然有限：此前的研究未拓展至高保真（HiFi）44.1kHz领域，存在频谱不连续、高频区域模糊的问题，同时对域外数据缺乏鲁棒性。这些局限限制了模型在音乐生成、歌声生成等多样化场景中的应用。本研究提出EVA-GAN（通过可扩展生成对抗网络实现的增强型多样化音频生成），通过使用36000小时的44.1kHz音频大规模数据集、上下文感知模块、人在环人工制品测量工具包，并将模型扩展至约2亿参数，在频谱重建、高频重建以及域外数据性能鲁棒性方面均较此前的最优水平实现显著提升，可生成高保真音频。研究演示可访问https://double-blind-eva-gan.cc查看。
英文摘要：
The advent of Large Models marks a new era in machine learning, significantly outperforming smaller models by leveraging vast datasets to capture and synthesize complex patterns. Despite these advancements, the exploration into scaling, especially in the audio generation domain, remains limited, with previous efforts didn't extend into the high-fidelity (HiFi) 44.1kHz domain and suffering from both spectral discontinuities and blurriness in the high-frequency domain, alongside a lack of robustness against out-of-domain data. These limitations restrict the applicability of models to diverse use cases, including music and singing generation. Our work introduces Enhanced Various Audio Generation via Scalable Generative Adversarial Networks (EVA-GAN), yields significant improvements over previous state-of-the-art in spectral and high-frequency reconstruction and robustness in out-of-domain data performance, enabling the generation of HiFi audios by employing an extensive dataset of 36,000 hours of 44.1kHz audio, a context-aware module, a Human-In-The-Loop artifact measurement toolkit, and expands the model to approximately 200 million parameters. Demonstrations of our work are available at https://double-blind-eva-gan.cc.
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。
