基于正样本与无标记样本学习的音频信号增强
Audio Signal Enhancement with Learning from Positive and Unlabelled Data
AI总结：
针对音频信号增强中并行训练数据合成失真、干净信号难获取的问题，提出用噪声频谱块作正样本、含噪信号频谱块作无标记样本的PU学习方法，训练卷积神经网络分类频谱块以实现增强。
摘要：
监督学习是音频信号增强（SE）的主流方法，需要由含噪信号与对应干净信号组成的并行训练数据。这类数据只能通过合成得到，与真实数据存在分布 mismatch（不匹配），会导致模型在真实数据上表现不佳。此外，在某些场景下可能无法获取干净信号，使得这种传统方法不可行。本文探索使用由含噪信号和噪声组成的非并行训练数据进行SE，这类数据易于采集。我们将正类（P）和负类（N）分别定义为信号非活跃状态和信号活跃状态。我们观察到，噪声片段的频谱图块可作为P类数据，含噪信号片段的频谱图块可作为无标记数据。因此，基于正样本与无标记样本的学习可使卷积神经网络学习将每个频谱图块分类为P类或N类，从而实现音频信号增强。
英文摘要：
Supervised learning is a mainstream approach to audio signal enhancement (SE) and requires parallel training data consisting of both noisy signals and the corresponding clean signals. Such data can only be synthesised and are mismatched with real data, which can result in poor performance on real data. Moreover, clean signals may be inaccessible in certain scenarios, which renders this conventional approach infeasible. Here we explore SE using non-parallel training data consisting of noisy signals and noise, which can be easily recorded. We define the positive (P) and the negative (N) classes as signal inactivity and activity, respectively. We observe that the spectrogram patches of noise clips can be used as P data and those of noisy signal clips as unlabelled data. Thus, learning from positive and unlabelled data enables a convolutional neural network to learn to classify each spectrogram patch as P or N to enable SE.
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。
