Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing artifacts in adverse conditions. In comparison, in such difficult scenarios, predictive models typically do not produce such artifacts but tend to distort the target speech instead, thereby degrading the speech quality. In this work, we present a stochastic regeneration approach where an estimate given by a predictive model is provided as a guide for further diffusion. We show that the proposed approach uses the predictive model to remove the vocalizing and breathing artifacts while producing very high quality samples thanks to the diffusion model, even in adverse conditions. We further show that this approach enables to use lighter sampling schemes with fewer diffusion steps without sacrificing quality, thus lifting the computational burden by an order of magnitude. Source code and audio examples are available online (https://uhh.de/inf-sp-storm).

Single-channel deep speech enhancement approaches often estimate a single multiplicative mask to extract clean speech without a measure of its accuracy. Instead, in this work, we propose to quantify the uncertainty associated with clean speech estimates in neural network-based speech enhancement. Predictive uncertainty is typically categorized into aleatoric uncertainty and epistemic uncertainty. The former accounts for the inherent uncertainty in data and the latter corresponds to the model uncertainty. Aiming for robust clean speech estimation and efficient predictive uncertainty quantification, we propose to integrate statistical complex Gaussian mixture models (CGMMs) into a deep speech enhancement framework. More specifically, we model the dependency between input and output stochastically by means of a conditional probability density and train a neural network to map the noisy input to the full posterior distribution of clean speech, modeled as a mixture of multiple complex Gaussian components. Experimental results on different datasets show that the proposed algorithm effectively captures predictive uncertainty and that combining powerful statistical models and deep learning also delivers a superior speech enhancement performance.

Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where missing data is generated based on existing data. Phase retrieval is inherently an imputation problem, where phase information has to be generated based on the given magnitude. In this work we build upon previous work in the speech domain, adapting a speech enhancement diffusion model specifically for STFT phase retrieval. Evaluation using speech quality and intelligibility metrics shows the diffusion approach is well-suited to the phase retrieval task, with performance surpassing both classical and modern methods.

In a scenario with multiple persons talking simultaneously, the spatial characteristics of the signals are the most distinct feature for extracting the target signal. In this work, we develop a deep joint spatial-spectral non-linear filter that can be steered in an arbitrary target direction. For this we propose a simple and effective conditioning mechanism, which sets the initial state of the filter's recurrent layers based on the target direction. We show that this scheme is more effective than the baseline approach and increases the flexibility of the filter at no performance cost. The resulting spatially selective non-linear filters can also be used for speech separation of an arbitrary number of speakers and enable very accurate multi-speaker localization as we demonstrate in this paper.

Diffusion-based generative models have had a high impact on the computer vision and speech processing communities these past years. Besides data generation tasks, they have also been employed for data restoration tasks like speech enhancement and dereverberation. While discriminative models have traditionally been argued to be more powerful e.g. for speech enhancement, generative diffusion approaches have recently been shown to narrow this performance gap considerably. In this paper, we systematically compare the performance of generative diffusion models and discriminative approaches on different speech restoration tasks. For this, we extend our prior contributions on diffusion-based speech enhancement in the complex time-frequency domain to the task of bandwith extension. We then compare it to a discriminatively trained neural network with the same network architecture on three restoration tasks, namely speech denoising, dereverberation and bandwidth extension. We observe that the generative approach performs globally better than its discriminative counterpart on all tasks, with the strongest benefit for non-additive distortion models, like in dereverberation and bandwidth extension. Code and audio examples can be found online at https://uhh.de/inf-sp-sgmsemultitask

最近，基于扩散的生成模型已引入语音增强的任务。干净的语音损坏被建模为固定的远期过程，其中逐渐添加了越来越多的噪声。通过学习以嘈杂的输入为条件的迭代方式扭转这一过程，可以产生干净的语音。我们以先前的工作为基础，并在随机微分方程的形式主义中得出训练任务。我们对基础分数匹配目标进行了详细的理论综述，并探索了不同的采样器配置，以解决测试时的反向过程。通过使用自然图像生成文献的复杂网络体系结构，与以前的出版物相比，我们可以显着提高性能。我们还表明，我们可以与最近的判别模型竞争，并在评估与培训不同的语料库时获得更好的概括。我们通过主观的听力测试对评估结果进行补充，其中我们提出的方法是最好的。此外，我们表明所提出的方法在单渠道语音覆盖中实现了出色的最新性能。我们的代码和音频示例可在线获得，请参见https://uhh.de/inf-sp-sgmse

由于不同的人对他人的情感表达方式有所不同，因此他们在唤醒和价值方面的注释本身是主观的。为了解决这个问题，这些情绪注释通常由多个注释者收集，并在注释者之间平均，以获取唤醒和价值的标签。但是，除了平均水平外，标签的不确定性也令人感兴趣，还应对自动情绪识别进行建模和预测。在文献中，为简单起见，标签不确定性建模通常以高斯对收集的注释的假设进行处理。但是，由于注释者的数量通常由于资源限制而相当小，因此我们认为高斯方法是一个相当粗略的假设。相比之下，在这项工作中，我们建议使用学生的T分布来对标签分布进行建模，这使我们可以考虑可用的注释数量。使用此模型，我们将基于相应的Kullback-Leibler差异函数得出相应的损失函数，并使用它来训练估计器以分布情绪标签，从中可以推断出平均值和不确定性。通过定性和定量分析，我们显示了T分布比高斯分布的好处。我们在AVEC'16数据集上验证了我们提出的方法。结果表明，我们基于T分布的方法对高斯方法进行了改进，而最新的不确定性建模会导致基于语音的情绪识别以及最佳甚至更快的收敛性。

使用多个麦克风进行语音增强的主要优点是，可以使用空间滤波来补充节奏光谱处理。在传统的环境中，通常单独执行线性空间滤波（波束形成）和单通道后过滤。相比之下，采用深层神经网络（DNN）有一种趋势来学习联合空间和速度 - 光谱非线性滤波器，这意味着对线性处理模型的限制以及空间和节奏单独处理的限制光谱信息可能可以克服。但是，尚不清楚导致此类数据驱动的过滤器以良好性能进行多通道语音增强的内部机制。因此，在这项工作中，我们通过仔细控制网络可用的信息源（空间，光谱和时间）来分析由DNN实现的非线性空间滤波器的性质及其与时间和光谱处理的相互依赖性。我们确认了非线性空间处理模型的优越性，该模型在挑战性的扬声器提取方案中优于Oracle线性空间滤波器，以低于0.24的POLQA得分，较少数量的麦克风。我们的分析表明，在特定的光谱信息中应与空间信息共同处理，因为这会提高过滤器的空间选择性。然后，我们的系统评估会导致一个简单的网络体系结构，该网络体系结构在扬声器提取任务上的最先进的网络体系结构优于0.22 POLQA得分，而CHIME3数据上的POLQA得分为0.32。

隔离架构在语音分离中显示出非常好的结果。像其他学习的编码器模型一样，它使用了短帧，因为它们已被证明在这些情况下可以获得更好的性能。这导致输入处有大量帧，这是有问题的。由于隔离器是基于变压器的，因此其计算复杂性随着较长的序列而大大增加。在本文中，我们在语音增强任务中采用了隔离器，并表明，通过以短期傅立叶变换（STFT）表示替换学习式编码器的功能，我们可以使用长帧而不会损害感知增强性能。我们获得了同等的质量和清晰度评估得分，同时将10秒的话语减少了大约8倍。

采用深层神经网络（DNN）直接学习多通道语音增强的过滤器，这可能是将线性空间过滤器与独立的节奏光谱后过滤器相结合的传统方法的两个关键优势：1）非线性空间过滤器克服源自线性处理模型的潜在限制和2）空间和速度光谱信息的关节处理可以利用不同信息来源之间的相互依赖性。最近提出了各种基于DNN的非线性过滤器，报告了良好的增强性能。但是，对于将网络体系结构设计变成机会游戏的内部机制知之甚少。因此，在本文中，我们执行实验，以更好地了解基于DNN的非线性过滤器对空间，光谱和时间信息的内部处理。一方面，我们在艰难的语音提取方案中的实验证实了非线性空间滤波的重要性，该空间过滤的重要性超过了Oracle线性空间滤波器，高于0.24 POLQA得分。另一方面，我们证明了联合处理导致较大的性能差距，除了空间信息之外，在利用光谱与时间信息的网络体系结构之间得分为0.4 POLQA得分。