论文标题
在现实情况下对基于神经网络的深度语音增强系统的主观评估
Subjective Evaluation of Deep Neural Network Based Speech Enhancement Systems in Real-World Conditions
论文作者
论文摘要
将两个低延迟深神经网络（DNN）的主观评估结果与传统基于Wiener滤波器抑制器的成熟版本进行比较。目标用例是现实世界中的单渠道语音增强应用程序，例如通信。包括由添加剂固定和非平稳噪声类型组成的现实世界记录。评估分为四个结果：语音质量，噪声透明度，语音清晰度或听力工作以及噪声级别W.R.T.演讲。结果表明，与传统的Wiener-Filter基线相比，DNN在所有条件下都改善了噪声的抑制，而不会在语音质量和噪声透明度上重大降低，同时比基线更好地保持语音清晰度。
Subjective evaluation results for two low-latency deep neural networks (DNN) are compared to a matured version of a traditional Wiener-filter based noise suppressor. The target use-case is real-world single-channel speech enhancement applications, e.g., communications. Real-world recordings consisting of additive stationary and non-stationary noise types are included. The evaluation is divided into four outcomes: speech quality, noise transparency, speech intelligibility or listening effort, and noise level w.r.t. speech. It is shown that DNNs improve noise suppression in all conditions in comparison to the traditional Wiener-filter baseline without major degradation in speech quality and noise transparency while maintaining speech intelligibility better than the baseline.
