arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00624eess.AScs.AIcs.LG
收藏

快速DCTTS:高效的深度卷积文本转语音

Fast DCTTS: Efficient Deep Convolutional Text-to-Speech

KAIST(韩国科学技术院)

Minsu Kang, Jihyun Lee, Simin Kim, Injung Kim

摘要:

我们提出了一个端到端的语音合成器,快速DCTTS,在一个单一的CPU线程上实时合成语音。该模型由一个精心调整的轻量级网络组成,该网络通过应用多个网络简化和保真度改进技术而设计。此外,我们提出了一种新的组高速公路激活,可以在计算效率和门控机制的正则化效果之间进行折衷。此外,我们引入了一个新的度量称为弹性梅尔倒频谱失真(EMCD)来衡量输出梅尔频谱图的保真度。在实验中,我们分析了加速技术对速度和语音质量的影响。与基线模型相比,该模型的MOS值从2.62提高到2.74,计算量仅为1.76%,参数仅为2.75%。单CPU线程运行速度提高了7.45倍,足以在不使用GPU的情况下实时生成梅尔频谱图。

英文摘要:

We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweight network designed by applying multiple network reduction and fidelity improvement techniques. In addition, we propose a novel group highway activation that can compromise between computational efficiency and the regularization effect of the gating mechanism. As well, we introduce a new metric called Elastic mel-cepstral distortion (EMCD) to measure the fidelity of the output mel-spectrogram. In experiments, we analyze the effect of the acceleration techniques on speed and speech quality. Compared with the baseline model, the proposed model exhibits improved MOS from 2.62 to 2.74 with only 1.76% computation and 2.75% parameters. The speed on a single CPU thread was improved by 7.45 times, which is fast enough to produce mel-spectrogram in real time without GPU.

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。

↑