Preliminary inversion mapping results with a new EMA corpus

Preliminary inversion mapping results with a new EMA corpus
复制标题

DOI:
10.21437/interspeech.2009-724
复制
发表时间:
2009
期刊:
--
影响因子:
--
通讯作者:
Korin Richmond
Korin Richmond
中科院分区:
其他
文献类型:
--
作者:
Korin Richmond

文献摘要

被引文献

相似文献

在本文中,我们应用我们的反演映射方法,轨迹混合密度网络(TMDN),一个新的语料库的发音数据,记录与卡斯滕斯AG500电磁关节描记器。这个新的数据集mngu0相对较大,语音丰富,还有其他有益的特征。我们获得了良好的结果,与均方根(RMS)的误差只有0.99毫米。这与我们之前MOCHA fsew0 EMA数据的等效线圈的最低结果1.54 mm RMS误差相比非常好。我们认为这表明mngu0数据集可能比fsew0数据集更一致,并且对于需要发音轨迹数据的研究非常有用。它也支持我们的观点,TMDN是非常适合反演映射问题。索引术语:声学发音,反演映射,神经网络。
In this paper, we apply our inversion mapping method, the trajectory mixture density network (TMDN), to a new corpus of articulatory data, recorded with a Carstens AG500 electromagnetic articulograph. This new data set, mngu0, is relatively large and phonetically rich, among other beneficial characteristics. We obtain good results, with a root mean square (RMS) error of only 0.99mm. This compares very well with our previous lowest result of 1.54mm RMS error for equivalent coils of the MOCHA fsew0 EMA data. We interpret this as showing the mngu0 data set is potentially more consistent than the fsew0 data set, and is very useful for research which calls for articulatory trajectory data. It also supports our view that the TMDN is very much suited to the inversion mapping problem. Index Terms: acoustic-articulatory, inversion mapping, neural network.