arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.08562cs.LGcs.SDeess.AS
收藏

潜在自回归声源分离

Latent Autoregressive Source Separation

Sapienza University of Rome(罗马第一大学);Ca’ Foscari University of Venice(威尼斯大学)

Emilian Postolache, Giorgio Mariani, Michele Mancusi, Andrea Santilli, Luca Cosmo, Emanuele Rodolà

摘要:

自回归模型在发电质量和下游任务性能方面在广泛的领域取得了令人印象深刻的结果。在连续域中,这种成功背后的关键因素是量化潜在空间的使用(例如,通过VQ-VAE自动编码器获得),这允许降维和更快的推理时间。然而,使用现有的预训练模型来执行新的非平凡任务是困难的,因为它需要额外的微调或广泛的训练来引发提示。本文介绍了LASS作为执行矢量量化潜在自回归声源分离(即,将输入信号去混合成其组成源),而不需要对现有模型进行附加的基于梯度的优化或修改。我们的分离方法依赖于贝叶斯公式,其中自回归模型是先验的,通过对加数令牌的潜在和进行频率计数来构建离散(非参数)似然函数。我们使用多种采样策略(例如,祖先的、束搜索)在分离质量方面显示出与现有方法竞争的结果,同时在推理时间和对更高维数据的可扩展性方面提供显著的加速。

英文摘要:

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow for dimensionality reduction and faster inference times. However, using existing pre-trained models to perform new non-trivial tasks is difficult since it requires additional fine-tuning or extensive training to elicit prompting. This paper introduces LASS as a way to perform vector-quantized Latent Autoregressive Source Separation (i.e., de-mixing an input signal into its constituent sources) without requiring additional gradient-based optimization or modifications of existing models. Our separation method relies on the Bayesian formulation in which the autoregressive models are the priors, and a discrete (non-parametric) likelihood function is constructed by performing frequency counts over latent sums of addend tokens. We test our method on images and audio with several sampling strategies (e.g., ancestral, beam search) showing competitive results with existing approaches in terms of separation quality while offering at the same time significant speedups in terms of inference time and scalability to higher dimensional data.

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。

↑