arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07379cs.SDeess.AS
收藏

基于信源滤波器的神经声码器混响建模

Reverberation Modeling for Source-Filter-based Neural Vocoder

University of Science and Technology of China(中国科学技术大学);National Institute of Informatics(国立信息学研究所);University of Edinburgh(爱丁堡大学)

Yang Ai, Xin Wang, Junichi Yamagishi, Zhen-Hua Ling

摘要:

本文提出了一种混响模块的源滤波器为基础的神经声码器,提高混响效果建模的性能。该模块使用神经声码器的输出波形作为输入,并通过将输入与房间脉冲响应(RIR)卷积来产生混响波形。我们提出了两种方法来参数化和估计RIR。第一种方法假设全局时不变(GTI)RIR,并直接在训练数据集上学习RIR的值。第二种方法假设话语级时变(UTV)RIR,其在一个话语内是不变的,但在话语之间变化,并且使用另一个神经网络来预测RIR值。我们将建议的混响模块添加到HiNet声码器的相位谱预测器(PSP)中,并联合训练模型。实验结果表明,该模型有助于混响效果的建模和提高混响语音的感知质量。UTV-RIR比GTI-RIR对未知混响条件具有更好的鲁棒性,并获得了更好的混响效果。

英文摘要:

This paper presents a reverberation module for source-filter-based neural vocoders that improves the performance of reverberant effect modeling. This module uses the output waveform of neural vocoders as an input and produces a reverberant waveform by convolving the input with a room impulse response (RIR). We propose two approaches to parameterizing and estimating the RIR. The first approach assumes a global time-invariant (GTI) RIR and directly learns the values of the RIR on a training dataset. The second approach assumes an utterance-level time-variant (UTV) RIR, which is invariant within one utterance but varies across utterances, and uses another neural network to predict the RIR values. We add the proposed reverberation module to the phase spectrum predictor (PSP) of a HiNet vocoder and jointly train the model. Experimental results demonstrate that the proposed module was helpful for modeling the reverberation effect and improving the perceived quality of generated reverberant speech. The UTV-RIR was shown to be more robust than the GTI-RIR to unknown reverberation conditions and achieved a perceptually better reverberation effect.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑