无需配对数据，仅用混响信号就能有效去除混响
U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model
- 基于最大似然框架设计序列学习策略，联合估计声学参数与原始语音
- 仅需100个带参数标注的混响样本，性能超越无监督基线
- 适合数据稀缺场景，如真实环境语音处理或资源受限设备
本文研究了在从弱监督到近乎无监督的多种监督设置下，训练先进去混响模型的效果，仅依赖混响信号和声学模型进行训练。现有深度学习方法通常需要成对的干信号与混响信号，但实际获取困难。本文提出一种受最大似然公式启发的序列学习策略，利用深度神经网络从混响输入中估计声学参数与干信号，并通过混响匹配损失进行引导。最高效变体仅需100个混响参数标注样本，即优于无监督基线，证明该方法在低资源场景下的有效性与实用性。
原文摘要 · Abstract (English)
This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a maximum-likelihood formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. Our most data-efficient variant requires only 100 reverberation-parameter-labeled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。