@article{oai:nagoya.repo.nii.ac.jp:00025726,
 author = {Tobing, Patrick Lumban and Kobayashi, Kazuhiro and Toda, Tomoki},
 issue = {12},
 journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
 month = {Nov},
 note = {In this paper, we present an innovative way of utilizing the natural relationship between speech sounds and articulatory movements by developing an articulatory controllable speech modification system. Specifically, we employ statistical acoustic-to-articulatory inversion mapping and articulatory-to-acoustic production mapping based on a Gaussian mixture model, allowing flexible modification of the model parameters and the independence of the text input features. Modification of an input speech signal through manipulation of the unobserved articulatory movements is achievable through a sequence of inversion and production mappings. To ensure the naturalness of articulatory movement trajectories, we introduce a method for manipulating articulatory parameters by considering their intercorrelation. Moreover, to generate high-quality modified speech sounds, we avoid the use of vocoder-based excitation generation by presenting several implementations of direct waveform modification capable of directly filtering an input speech signal using the differences in spectral parameters. The experimental results demonstrate that: 1) higher accuracy in the estimation of spectral parameters is achieved by using sequential inversion and production mappings than for conventional production mapping using measured articulatory parameters, 2) the method for manipulating articulatory parameters by considering their intercorrelation makes it possible to generate more natural trajectories of modified articulatory movements; 3) the implementations of the direct waveform modification method significantly improve the quality of modified speech sounds, even under varying speaking conditions; and 4) the controllability of the system is ensured by its capability of producing modified vowel sounds through the manipulation of appropriate articulatory configurations.},
 pages = {2337--2350},
 title = {Articulatory Controllable Speech Modification Based on Statistical Inversion and Production Mappings},
 volume = {25},
 year = {2017}
}