Related papers: How far are vowel formants from computed vocal tra…
In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand…
In the presented study, a numerical model which predicts the flow-induced collapse within the pharyngeal airway is validated using in vitro measurements. Theoretical simplifications were considered to limit the computation time. Systematic…
Vowels are primarily characterized by tongue position. Humans have discovered these features of vowel articulation through their own experience and explicit objective observation such as using MRI. With this knowledge and our experience, we…
Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current…
This paper addresses the challenging scenario for the distant-talking control of a music playback device, a common portable speaker with four small loudspeakers in close proximity to one microphone. The user controls the device through…
Accurate segmentation of articulatory structures in real-time MRI (rtMRI) remains challenging, as existing methods rely primarily on visual cues and overlook complementary information from synchronized speech signals. We propose VocSegMRI,…
An analysis is developed linking the form of the sound field from a circular source to the radial structure of the source, without recourse to far-field or other approximations. It is found that the information radiated into the field is…
A 3D biomechanical dynamical model of human tongue is presented, that is elaborated in the aim to test hypotheses about speech motor control. Tissue elastic properties are accounted for in Finite Element Modeling (FEM). The FEM mesh was…
We consider a class of Hamiltonian PDEs that can be split into a linear unbounded operator and a regular non linear part, and we analyze their numerical discretizations by symplectic methods when the initial value is small in Sobolev norms.…
We propose ARTI-6, a compact six-dimensional articulatory speech encoding framework derived from real-time MRI data that captures crucial vocal tract regions including the velum, tongue root, and larynx. ARTI-6 consists of three components:…
For 6-DOF (degrees of freedom) interactive virtual acoustic environments (VAEs), the spatial rendering of diffuse late reverberation in addition to early (specular) reflections is important. In the interest of computational efficiency, the…
Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…
So far, several physical models have been proposed for the study of vocal fold oscillations during phonation. The parameters of these models, such as vocal fold elasticity, resistance, etc. are traditionally determined through the…
It is described, explicitly, how a popular, commercially-available software package for solving partial-differential-equations (PDEs), as based on the finite-element method (FEM), can be configured to calculate the frequencies and fields of…
Accurate tooth volume segmentation is a prerequisite for computer-aided dental analysis. Deep learning-based tooth segmentation methods have achieved satisfying performances but require a large quantity of tooth data with ground truth. The…
The tongue's intricate 3D structure, comprising localized functional units, plays a crucial role in the production of speech. When measured using tagged MRI, these functional units exhibit cohesive displacements and derived quantities that…
Music composition using digital audio sequence editors is increasingly performed in a visual workspace where sound complexes are built from discrete sound objects, called gestures that are arranged in time and space to generate a continuous…
We present a model for predicting articulatory features from surface electromyography (EMG) signals during speech production. The proposed model integrates convolutional layers and a Transformer block, followed by separate predictors for…
In spoken languages, speakers divide up the space of phonetic possibilities into different regions, corresponding to different phonemes. We consider a simple exemplar model of how this division of phonetic space varies over time among a…
Available algorithms for the initialization of volume fractions typically utilize exact functions to model fluid interfaces, or they rely on computationally costly intersections between volume meshes. Here, a new algorithm is proposed that…