Listening test materials for "Smooth Talking: Articulatory Join Costs for Unit Selection"

This is the listening test data for the experiment presented in the ICASSP 2016 paper "Smooth Talking: Articulatory Join Costs for Unit Selection", which proposes and evaluates computation of unit selection join costs in the articulatory domain. Join cost calculation has so far dealt exclusively with acoustic speech parameters, and a large number of distance metrics have previously been tested in conjunction with a wide variety of acoustic parameterisations. In contrast, we propose here to calculate distance in articulatory space. The motivation for this is simple: physical constraints mean a human talker's mouth cannot ``jump'' from one configuration to a different one, so smooth evolution of articulator positions would also seem desirable for a good candidate unit sequence. To test this, we built Festival Multisyn voices using a large articulatory-acoustic dataset. We first synthesised 460 TIMIT sentences and confirmed our articulatory join cost gives appreciably different unit sequences compared to the standard Multisyn acoustic join cost. A listening test (3 sets of 25 sentence pairs, 30 listeners) then showed our articulatory cost is preferred at a rate of 58% compared to the standard Multisyn acoustic join cost.

本数据集为2016年国际声学、语音与信号处理会议（ICASSP 2016）收录的论文《Smooth Talking: Articulatory Join Costs for Unit Selection》中所述实验的听音测试数据，该论文提出并评估了发音域（articulatory domain）下的单元选择拼接代价计算方法。此前，拼接代价的计算仅局限于声学语音参数领域，且已有大量距离度量方法结合多种声学参数配置方案完成了验证。与之相对，本文提出在发音空间（articulatory space）中计算距离。这一思路的动机十分直观：物理约束决定了人类发声者的口腔无法从一种发声构型直接“跳转”至另一种，因此，对于优质的候选单元序列而言，发音器官位置的平滑过渡同样是理想的特性。为验证该思路，我们基于大规模发音-声学数据集构建了Festival Multisyn语音合成系统。我们首先合成了460句TIMIT语料库（TIMIT）的句子，并证实相较于标准Multisyn声学拼接代价，我们提出的发音拼接代价能够生成差异显著的单元序列。随后开展的听音测试（共3组，每组包含25句句子对，30名受试者）结果显示，相较于标准Multisyn声学拼接代价，有58%的受试者更偏好我们提出的发音拼接代价。