论文标题
使用时间卷积复发神经网络的单个通道语音增强
Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks
论文作者
论文摘要
近几十年来，基于神经网络的方法显着改善了语音增强的性能。他们中的大多数人会直接或间接地估计目标语音的时频表示（T-F）表示，然后使用估计的t-f表示形式重新合成波形。在这项工作中，我们提出了时间卷积复发网络（TCRN），这是一个直接将噪声波形映射到清洁波形的端到端模型。 TCRN是合并的卷积和复发性神经网络，能够有效地利用短期ANG长期信息。 Futuremore，我们介绍了在远期传播期间反复逐渐简单示例演讲的架构。我们表明，与现有的卷积复发网络相比，我们的模型能够提高模型的性能。 Futuremore，我们提出了几种稳定培训过程的关键技术。实验结果表明，就语音清晰度和质量而言，我们的模型始终胜过现有的语音增强方法。
In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform using the estimated T-F representation. In this work, we proposed the temporal convolutional recurrent network (TCRN), an end-to-end model that directly map noisy waveform to clean waveform. The TCRN, which is combined convolution and recurrent neural network, is able to efficiently and effectively leverage short-term ang long-term information. Futuremore, we present the architecture that repeatedly downsample and upsample speech during forward propagation. We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks. Futuremore, We present several key techniques to stabilize the training process. The experimental results show that our model consistently outperforms existing speech enhancement approaches, in terms of speech intelligibility and quality.
