Robust noise reduction by novel means of incorporating phase processing

通过结合相位处理的新颖方法实现稳健的降噪

• 批准号: 247465126
• 负责人: Professor Dr.-Ing. Timo Gerkmann
• 金额: --
• 依托单位: Arbeitsbereich Signalverarbeitung (SP)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2014
• 资助国家: 德国
• 起止时间: 2013-12-31 至 2022-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/247465126?language=en
• 关键词: Robust; noise; reduction; novel; means

Today, speech communication devices including smart-phones, hearing aids and acoustic human-machine interfaces are ubiquitous. However, in many everyday situations, speech signals are distorted by acoustic noise, for example in a cafeteria or on a busy street. To reduce the negative impact of these disturbances on speech communication, speech enhancement algorithms are used. However, in the acoustically challenging scenarios in which speech enhancement algorithms would be needed most, the performance gain is still limited. Therefore, in this project we aim at making speech enhancement algorithms work more reliably to ease speech communication in acoustically difficult environments.Speech enhancement is usually applied in a spectral transform domain, in which the signal coefficients are complex-valued, i.e. they are represented by spectral amplitudes and phases. Still, most research on single-channel speech enhancement focused on spectral magnitudes while the spectral phase was largely ignored. However, recent research, including our work in the first funding period of this project, indicate that the importance of the spectral phase for speech enhancement might have been underestimated: with instrumental measures and in listening experiments we were able to show that an estimate of the clean speech spectral phase can be used to improve the speech enhancement performance, especially in challenging acoustic scenarios. Now, we aim at building up on these results and derive new and improved estimators of the clean speech spectral phase to improve performance further. For this, we will develop and combine individual phase estimators for voiced, unvoiced, and transient sounds. We will also translate recent advances in pre-trained speech enhancement, e.g., based on deep neural networks (DNNs), to phase processing. Currently, most pre-trained approaches rely only on magnitude features and also only modify the spectral magnitudes. Here, we aim at overcoming both limitations, for which we will investigate new phase features and how they can be employed, e.g. to build novel DNN based phase-aware speech enhancement systems. Our research will provide new and valuable insights into the role and relevance of phase processing for speech enhancement as well as novel algorithms that will boost the performance of speech communication devices.

今天，语音通信设备，包括智能手机，助听器和声学人机接口是无处不在的。然而，在许多日常情况下，语音信号被声学噪声失真，例如在自助餐厅或在忙碌的街道上。为了减少这些干扰对语音通信的负面影响，使用语音增强算法。然而，在声学上具有挑战性的情况下，语音增强算法将是最需要的，性能增益仍然是有限的。因此，在这个项目中，我们的目标是使语音增强算法更可靠地工作，以减轻语音通信在声学困难的environments.Speech增强通常被应用在频谱变换域，其中的信号系数是复值，即它们表示的频谱幅度和相位。然而，大多数单通道语音增强的研究集中在频谱幅度，而频谱相位在很大程度上被忽略。 然而，最近的研究，包括我们在该项目的第一个资助期的工作，表明语音增强的频谱相位的重要性可能被低估了：通过仪器测量和听力实验，我们能够证明，对干净语音频谱相位的估计可以用来提高语音增强性能，特别是在具有挑战性的声学场景中。现在，我们的目标是建立在这些结果，并获得新的和改进的估计的干净的语音频谱相位，以进一步提高性能。为此，我们将开发和联合收割机个人的相位估计，有声，无声和瞬态声音。我们还将翻译预训练语音增强的最新进展，例如，基于深度神经网络（DNN）的相位处理。目前，大多数预训练方法仅依赖于幅度特征，并且仅修改频谱幅度。在这里，我们的目标是克服这两个限制，为此，我们将研究新的相位特征以及如何使用它们，例如构建基于DNN的新型相位感知语音增强系统。我们的研究将为语音增强的相位处理的作用和相关性以及提高语音通信设备性能的新算法提供新的和有价值的见解。