The article presents a statistical mapping approach for crossspeaker acoustic-to-articulatory inversion. The goal is to estimate the most likely articulatory trajectories for a reference speaker from the speech audio signal of another speaker. This approach is developed in the framework of our system of visual articulatory feedback developed for computer-assisted pronunciation training applicat...

The context of this work is speech analysis. The subject deals with acoustic-to-articulatory inversion, i.e. the recovery of the temporal evolution of the vocal tract shape from the signal. This topic is important because it is likely to give rise to applications in the domains of speech coding as well as second language learning. Acoustic-to-articulatory inversion relies on an analysis by synt...

We studied mutual influences between native and non-native vowel production during learning, i.e., before and after short-term visual articulatory feedback training with non-native sounds. Monolingual French speakers were trained to produce two non-native vowels: the Danish /ɔ/, which is similar to the French /o/, and the Russian /ɨ/, which is dissimilar from French vowels. We examined relation...

This paper presents preliminary results on difference limen for articulatory parameters. An articulatory based speech synthesizer, TRACTTALK, is utilized to generate speech stimuli. Each time only one articulatory parameter is altered by a small amount. The synthetic speech is then randomized and presented to a group of listeners in the AB form. As expected, the results show that not all small ...

An attempt to define a new articulatory synthesis method, in which the speech signal is generated through a statistical estimation of its relation with articulatory parameters, is presented. A corpus containing acoustic material and simultaneous recordings of the tongue and facial movements was used to train and test the articulatory synthesis of VCV words and short sentences. Tongue and facial...

We present a novel multi-level HMM in which an intermediate ‘articulatory’ representation is included between the state and surface-acoustic levels. A potential difficulty with such a model is that advantages gained by the introduction of an articulatory layer might be compromised by limitations due to an insufficiently rich articulatory representation, or by compromises made for mathematical o...

In this study, a speaker-adaptive articulatory model was constructed by fitting point-wise articulatory positions measured by electromagnetic articulography (EMA) to the vocal tract framework in [5] to customize a standard vocal tract model with speaker-dependent articulatory features. With the speakeradaptive articulatory model, the area functions of oral and nasal vowel pairs (/a/, /i/, /u/) ...

We use mutual information as the criterion to rank the Mel frequency cepstral coefficients (MFCCs) and their derivatives according to the information they provide about different articulatory features in acoustic-to-articulatory (AtoA) inversion. It is found that just a small subset of the coefficients encodes maximal information about articulatory features and interestingly, this subset is art...

Recent literature in Articulatory Phonology (AP) has promoted the idea that tone is an articulatory gesture, similar to those that make up consonants and vowels (Prieto and Torreira 2007, Gao 2008). When treated as gestures, tones should be co-selected and coordinated like other articulatory gestures. The co-selection of T(one) gestures with C(onsonant) and V(owel) gestures is reminiscent of th...

PURPOSE To examine the effects and generalization of a modified script training intervention, delivered partly via videoconferencing, on dialogue scripts that were produced by 2 individuals with aphasia. METHOD Each participant was trained on 2 personally relevant scripts. Intervention sessions occurred 3 times per week, with a combination of in-person meetings and videoconferencing, and last...