Spatio-temporal articulatory movement primitives during speech production: Extraction, interpretation, and validation
Spatio-temporal articulatory movement primitives during speech production: Extraction, interpretation, and validation
复制标题
DOI：
10.1121/1.4812765
复制
发表时间：
2013-08-01
影响因子：
2.4
通讯作者：
Narayanan, Shrikanth S.
中科院分区：
文献类型：
--
作者：
Ramanarayanan, Vikram;Goldstein, Louis;Narayanan, Shrikanth S.
本文提出了一种从语音清晰度数据中提取可解释运动基元的计算方法。提出了一种具有稀疏约束的卷积非负矩阵分解算法(CNMFsc)，将给定的数据矩阵分解为一组时空基序列和一个激活矩阵。该算法优化了一个代价函数，该代价函数权衡了所提出的模型和输入数据与在任何给定时刻处于活动状态的基元数量之间的不匹配。该方法既适用于通过电磁关节造影术获得的测量的发音数据，也适用于使用发音合成器产生的合成数据。然后描述了如何定量地评估算法的性能，并进一步对算法从数据中恢复组成结构的能力进行了定性评估。这是使用由发音合成器基于节律音系框架生成的伪地面真实基元来完成的[Browman和Goldstein(1995)。《动力学和发音音系学》，《作为运动的头脑：认知动力学的探索》，R.F.波特和T.van Geld(麻省理工学院出版社，马萨诸塞州剑桥)编辑，第175-194页]。实验结果表明，该算法能够从人类语音生成数据中提取出语言上可解释的运动基元。这样的框架可能有助于理解言语产生中长期存在的问题，如运动控制和协同发音。(C)2013年美国声学学会。
This paper presents a computational approach to derive interpretable movement primitives from speech articulation data. It puts forth a convolutive Nonnegative Matrix Factorization algorithm with sparseness constraints (cNMFsc) to decompose a given data matrix into a set of spatiotemporal basis sequences and an activation matrix. The algorithm optimizes a cost function that trades off the mismatch between the proposed model and the input data against the number of primitives that are active at any given instant. The method is applied to both measured articulatory data obtained through electromagnetic articulography as well as synthetic data generated using an articulatory synthesizer. The paper then describes how to evaluate the algorithm performance quantitatively and further performs a qualitative assessment of the algorithm's ability to recover compositional structure from data. This is done using pseudo ground-truth primitives generated by the articulatory synthesizer based on an Articulatory Phonology frame-work [Browman and Goldstein (1995). "Dynamics and articulatory phonology," in Mind as motion: Explorations in the dynamics of cognition, edited by R. F. Port and T. van Gelder (MIT Press, Cambridge, MA), pp. 175-194]. The results suggest that the proposed algorithm extracts movement primitives from human speech production data that are linguistically interpretable. Such a framework might aid the understanding of long-standing issues in speech production such as motor control and coarticulation. (C) 2013 Acoustical Society of America.