Real-time vibration control of an electrolarynx based on statistical F0 contour prediction
Real-time vibration control of an electrolarynx based on statistical F0 contour prediction
复制标题
基于统计F0轮廓预测的电喉实时振动控制
DOI：
10.1109/eusipco.2016.7760465
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Satoshi Nakamura
中科院分区：
文献类型：
--
作者：
Kou Tanaka;Tomoki Toda;Graham Neubig;Satoshi Nakamura
电喉是一种助声设备，可以人工产生激励声音，帮助喉切除术患者产生电喉(EL)语音。虽然EL语音是相当容易理解的，但它的自然性明显受到机械激励声的非自然基频(F0)模式的影响。为了能够产生听起来更自然的EL语音，我们提出了一种基于统计F0预测的方法来自动控制从电喉产生的激励声音的F0模式，该方法实时地从产生的EL语音预测F0模式。在我们之前的工作中，我们通过在实际的物理电喉上实施所提出的实时预测方法来开发一个原型系统，通过使用该原型系统，我们发现原型系统对EL语音自然度的改善往往低于批量型预测。本文研究了实时预测的延迟对F0预测精度的负面影响，并提出了两种方法来缓解这些影响：1)分段连续F0模式的建模；2)对即将到来的F0值进行预测。实验结果表明：1)传统的实时预测方法需要较大的延迟来预测CF0模式；2)所提出的方法对实时预测有积极的影响。
An electrolarynx is a speaking aid device to artificially generate excitation sounds to help laryngectomees produce electrolaryngeal (EL) speech. Although EL speech is quite intelligible, its naturalness significantly suffers from the unnatural fundamental frequency (F0) patterns of the mechanical excitation sounds. To make it possible to produce more naturally sounding EL speech, we have proposed a method to automatically control F0patterns of the excitation sounds generated from the electrolarynx based on the statistical F0prediction, which predicts F0patterns from the produced EL speech in real-time. In our previous work, we have developed a prototype system by implementing the proposed real-time prediction method in an actual, physical electrolarynx, and through the use of the prototype system, we have found that improvements of the naturalness of EL speech yielded by the prototype system tend to be lower than that yielded by the batch-type prediction. In this paper, we examine negative impacts caused by latency of the real-time prediction on the F0prediction accuracy, and to alleviate them, we also propose two methods, 1) modeling of segmented continuous F0(CF0) patterns and 2) prediction of forthcoming F0values. The experimental results demonstrate that 1) the conventional real-time prediction method needs a large delay to predict CF0patterns and 2) the proposed methods have positive impacts on the real-time prediction.