arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.09573cs.SDeess.AS
收藏

一种用于统计参数语音合成的幅度和相位谱分层生成的神经声码器

A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis

Yang Ai, Zhen-Hua Ling

摘要:

本文提出了一种神经元声码器HiNet,它通过对幅度谱和相位谱的分层预测,从声学特征中重构语音波形。与现有的WaveNet、SampleRNN和WaveRNN等直接使用单个神经网络产生波形样本的神经声码器不同,HiNet声码器由幅度谱预测器(ASP)和相位谱预测器(PSP)组成。ASP是一个简单的DNN模型,它从声学特征预测对数振幅谱(LAS)。预测的LAS被发送到PSP中用于相位恢复。考虑到相位扭曲问题和相位建模的困难,PSP是通过级联一个神经源滤波器(NSF)波形发生器和相位提取器。我们还将生成对抗网络(GANs)引入ASP和PSP。最后,将ASP和PSP的输出结合起来,通过短时傅立叶合成来重构语音波形。由于两种预测器都没有自回归结构,HiNet声码器可以高效地产生语音波形。客观和主观的实验结果表明,我们提出的HiNet声码器实现了更好的自然度比传统的STRAIGHT声码器,一个16位的WaveNet声码器使用开源实现和NSF声码器具有类似的复杂度的PSP,并获得类似的性能与16位的WaverRNN声码器的重建语音。我们还发现,在一定程度上,HiNet的性能是不敏感的神经波形发生器在PSP中的复杂性。在简化其模型结构后,使用GPU生成16kHz语音的1s波形所消耗的时间可以从0.34s进一步减少到0.19s,而不会显着降低质量。

英文摘要:

This paper presents a neural vocoder named HiNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra hierarchically. Different from existing neural vocoders such as WaveNet, SampleRNN and WaveRNN which directly generate waveform samples using single neural networks, the HiNet vocoder is composed of an amplitude spectrum predictor (ASP) and a phase spectrum predictor (PSP). The ASP is a simple DNN model which predicts log amplitude spectra (LAS) from acoustic features. The predicted LAS are sent into the PSP for phase recovery. Considering the issue of phase warping and the difficulty of phase modeling, the PSP is constructed by concatenating a neural source-filter (NSF) waveform generator with a phase extractor. We also introduce generative adversarial networks (GANs) into both ASP and PSP. Finally, the outputs of ASP and PSP are combined to reconstruct speech waveforms by short-time Fourier synthesis. Since there are no autoregressive structures in both predictors, the HiNet vocoder can generate speech waveforms with high efficiency. Objective and subjective experimental results show that our proposed HiNet vocoder achieves better naturalness of reconstructed speech than the conventional STRAIGHT vocoder, a 16-bit WaveNet vocoder using open source implementation and an NSF vocoder with similar complexity to the PSP and obtains similar performance with a 16-bit WaveRNN vocoder. We also find that the performance of HiNet is insensitive to the complexity of the neural waveform generator in PSP to some extend. After simplifying its model structure, the time consumed for generating 1s waveforms of 16kHz speech using a GPU can be further reduced from 0.34s to 0.19s without significant quality degradation.

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。

↑