@techreport{aryal2012techreport,

title = {Articulatory Inversion and Synthesis: Towards Articulatory-Based Modification of Speech},

author = {S Aryal and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2012techreport.pdf},

year  = {2012},

date = {2012-12-04},

abstract = {Certain speech modifications, such as changes in foreign/regional accents or articulatory styles, are performed more effectively in the articulatory domain than in the acoustic domain. Though measuring articulators is cumbersome, articulatory parameters may be estimated from acoustics through inversion. In this paper, we study the impact on synthesis quality when articulators predicted from acoustics are used in articulatory synthesis. For this purpose, we trained a GMM articulatory synthesizer and drove it with articulators predicted with an RBF-based inversion model. Using inverted instead of measured articulators degraded synthesis quality, as measured through Mel cepstral distortion and subjective tests. However, retraining the synthesizer with predicted articulators not only reversed the effect of errors introduced during inversion but also improved synthesis quality relative to using measured articulators. These results suggest that inverted articulators do not compromise synthesis quality, and open up the possibility of performing speech modification in the articulatory domain through inversion.},

keywords = {Articulatory inversion, Articulatory synthesis, Speech},

pubstate = {published},

tppubtype = {techreport}

}

@techreport{aryal2012techreport-2,

title = {Boosting Automatic Speech Recognition through Articulatory Inversion},

author = {S Aryal and J Huang and D Felps and R Gutierrez-Osuna},

url = {https://psi.engr.tamu.edu/wp-content/uploads/2018/01/aryal2012techreport-2.pdf},

year  = {2012},

date = {2012-12-04},

abstract = {This paper explores whether articulatory features predicted from speech acoustics through inversion may be used to boost the recognition of context-dependent units when combined with acoustic features. For this purpose, we performed articulatory inversion on a corpus containing acoustic and electromagnetic articulography recordings from a single speaker. We then compared the performance of an HMM-based diphone classifier on the individual feature sets (acoustic, articulatory, inversion) as well as on their combinations. To make good use of the limited corpus, we used a factorized representation that first classified diphones into broad overlapping categories and then combined them using a maximum-a-posteriori criterion. When comparing the individual feature sets, our results show no degradation in classification performance when predicted articulators are used instead of ground-truth articulators. Further, performance on the acoustic feature set improved by 10% when adding ground-truth articulators and by 5% when adding predicted articulators.},

keywords = {Articulatory inversion},

pubstate = {published},

tppubtype = {techreport}

}