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 2203.01080cs.SDeess.AS
收藏

基于GAN的非自回归TTS多尺度时频谱图鉴别器

A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

The Chinese University of Hong Kong(香港中文大学)

Haohan Guo, Hui Lu, Xixin Wu, Helen Meng

摘要:

生成对抗网络(GAN)通过使用区分真实语音和生成语音的额外模型进行对抗训练,在改善非自回归TTS(NAR-TTS)方面表现出了出色的能力。为了最大限度地发挥GAN的优势,找到一种能够捕获丰富可区分信息的强大的搜索引擎至关重要。在本文中,我们提出了一个多尺度的时间-频率谱图的迭代,以帮助NAR-TTS生成高保真梅尔频谱图。它将频谱图视为二维图像,以利用时频域中不同分量之间的相关性。采用基于U-Net的模型结构在不同尺度下进行区分,以捕获粗粒度和细粒度的信息。我们进行主观测试,以评估所提出的方法。多尺度和时频鉴别技术的引入,大大提高了图像的自然度和逼真度。当结合神经声码器时,它比微调声码器更有效和简洁。最后,我们可视化的判别图,比较它们的差异,以验证多尺度判别的有效性。

英文摘要:

The generative adversarial network (GAN) has shown its outstanding capability in improving Non-Autoregressive TTS (NAR-TTS) by adversarially training it with an extra model that discriminates between the real and the generated speech. To maximize the benefits of GAN, it is crucial to find a powerful discriminator that can capture rich distinguishable information. In this paper, we propose a multi-scale time-frequency spectrogram discriminator to help NAR-TTS generate high-fidelity Mel-spectrograms. It treats the spectrogram as a 2D image to exploit the correlation among different components in the time-frequency domain. And a U-Net-based model structure is employed to discriminate at different scales to capture both coarse-grained and fine-grained information. We conduct subjective tests to evaluate the proposed approach. Both multi-scale and time-frequency discriminating bring significant improvement in the naturalness and fidelity. When combining the neural vocoder, it is shown more effective and concise than fine-tuning the vocoder. Finally, we visualize the discriminating maps to compare their difference to verify the effectiveness of multi-scale discriminating.

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。

↑