Exploring Critical Articulator Identification from 50Hz RT-MRI Data of the Vocal Tract

Abstract

The study of the static and dynamic aspects of speech production can profit from technologies such as electromagnetic midsagittal articulography (EMA) and real-time magnetic resonance (RTMRI). These can improve our knowledge on which articulators and gestures are involved in producing specific sounds and foster improved speech production models, paramount to advance, e.g., articulatory speech synthesis. Previous work, by the authors, has shown that critical articulator identification could be performed from RTMRI data of the vocal tract, with encouraging results, by extending the applicability of an unsupervised statistical identification method previously proposed for EMA data. Nevertheless, the slower time resolution of the considered RT-MRI corpus (14 Hz), when compared to EMA, potentially influencing the ability to select the most suitable representative configuration for each phone-paramount for strongly dynamic phones, e.g., nasal vowels-, and the lack of a richer set of contexts-relevant for observing coarticulation effects-, were identified as limitations. This article addresses these limitations by exploring critical articulator identification from a faster RTMRI corpus (50 Hz), for European Portuguese, providing a richer set of contexts, and testing how fusing the articulatory data of two speakers might influence critical articulator determination.

Data-Driven Critical Tract Variable Determination for European Portuguese

“…The TB is determined as the most critical articulator, for most vowels, in accordance to the descriptions available in the literature. The appearance of V, as critical articulator for some oral vowels, earlier than for nasals, is aligned with previous outcomes of the method [19,23,24]. This is probably due to a more stable position of V at the middle of oral vowels (the selected frame) than at the different stages selected for the nasal vowels for which it appears, mostly, in the fourth place, eventually due to the adopted conservative stopping criteria, to avoid phones without any reported critical articulator.…”

“…For the sake of space economy, in the tract variable listing the T and C were omitted, for example, TBCd became Bd. Concerning the 1D correlation, among the different variable dimensions (see Figure 6), the variables are, overall, more decorrelated than in previous approaches considering landmarks over the vocal tract (e.g., see Silva et al [24]) and has been further improved by the novel representation for the velar data considered in this work. The larger amount of data, in comparison with our first testing of the tract variable aligned with Articulatory Phonology [25], resulted in an even smaller number of correlations.…”

“…Since one frame is used as representative of the vocal tract configuration for each sound, a higher frame rate, might enable capturing key moments of articulation, for example, alveolar contact for the /n/. To address these aspects, in Silva et al [24], the authors explored 50Hz RT-MRI data showing both the applicability of the methods to the novel data along with noticeable improvement of the results. At this point, the representation of the vocal tract configurations was still being performed based on landmarks placed on the lips, tongue surface, and velum, to establish similar conditions as those of the method proposed for EMA.…”

“…Differently from the original application of the method to EMA [19] and subsequent extension to RT-MRI data by our team [24], for this work the considered variables are not landmarks placed over the vocal tract, but tract variables aligned with the Task Dynamics framework [27,37], that is, mostly based on the concepts of constrictions defined by their location and degree (distance). After preliminary work by the authors [25], which provided interesting results and has shown the applicability of the critical articulator method to this new set of variables, this work further extends this approach by also abandoning the landmark representation for the velum, identified as a limitation in our previous studies.…”

“…Similarly to Silva et al [24,25], and considering the dynamic nature of nasal vowels [8,34,38,39], we wanted to have some additional information to assert if, for different timepoints, the determination of the critical articulators would highlight any relevant differences in behavior. Therefore, each nasal vowel was represented by three "pseudo-phones", focusing the starting, middle and final frame of the annotated interval and named, respectively, [vowel] start , [vowel] mid and [vowel], as in:ã start ,ã mid , andã.…”