AURORA Model of Formant-to-Tongue Inversion for Didactic and Clinical Applications

Patrycja Strycharczuk; Sam Kirkham

cs.CLMar 18, 2026

AURORA Model of Formant-to-Tongue Inversion for Didactic and Clinical Applications

Authors: Patrycja Strycharczuk, Sam Kirkham

Organizations: University of Manchester · Lancaster University

Abstract

This paper outlines the conceptual and computational foundations of the AURORA (Acoustic Understanding and Real-time Observation of Resonant Articulations) model. AURORA predicts tongue displacement and shape in vowel sounds based on the first two formant values. It is intended as a didactic aid helping to explain the relationship between formants and the underlying articulation, as well as a foundation for biofeedback applications. The model is informed by ultrasound tongue imaging and acoustic data from 40 native speakers of English. In this paper we discuss the motivation for the model, the modelling objectives as well as the model architecture. We provide a qualitative evaluation of the model, focusing on selected tongue features. We then present two tools developed to make the model more accessible to a wider audience, a Shiny app and a prototype software for real-time tongue biofeedback. Potential users include students of phonetics, linguists in fields adjacent to phonetics, as well as speech and language therapy practitioners and clients.

Figures & tables

Panel of Figure 1 — Figure 1: Stages of tongue contour reconstruction from the output of multivariate regression

Figure 2: Tongue model predictions. Input $F_{1}$ and $F_{2}$ values are indicated on the strip labels. Tongue tip is on the left.

Figure 3: Comparison of tongue model predictions with mean tongue shapes for each item in the input data, based on the mean formant values. Tongue tip is on the left.

Figure 4: Screenshot of the Shiny app, showing the controls and the predicted output

Panel of Figure 5 — Figure 5: Screenshots of the acoustic/articulatory biofeedback app showing a production of /i/ (top) and / \textipa A/ (bottom). The left panel shows formant tracking based on the input spectrum and the middle panel shows a predicted tongue contour. The right panel shows controls, which can be hidden by the user.

Speech Processing

Speech processing develops computational methods for recognizing, synthesizing, analyzing, and transforming spoken audio.

See all 412 papers

A low-dimensional dynamical basis for tongue shape control
Oct 16, 2026Sam Kirkham, Patrycja StrycharczukSpeech Production Latent Dynamics Modeling
Phonetics Laboratory, Lancaster University, United Kingdom · Linguistics and English Language, University of Manchester, United Kingdom
Articulatory strategy as a source of variation in acoustic vowel dynamics
May 22, 2026Patrycja Strycharczuk, Justin J. H. Lo, Sam KirkhamSpeech Production
Linguistics and English Language, University of Manchester, United Kingdom · Linguistics and English Language, Lancaster University, United Kingdom
Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification
Aug 10, 2026Abner Hernandez, Tomás Arias Vergara, Daiqi Liu +2Speech Processing
Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen, Germany · Department of Electronic Engineering Universidad de Antioquia Medell´ın, Colombia

Oct 16, 2026J/K move · Enter open · S save

A low-dimensional dynamical basis for tongue shape control

Sam Kirkham, Patrycja Strycharczuk

Phonetics Laboratory, Lancaster University, United Kingdom · Linguistics and English Language, University of Manchester, United Kingdom

Speech Production Latent Dynamics Modeling

Open paper AskPDF arXiv

Speech production involves the control of a high-dimensional articulatory system with many degrees-of-freedom, but a widespread hypothesis is that speakers navigate this complexity using a set of lower-dimensional control variables. Common candidates for these control variables include individual articulators (e.g. tongue body) and abstract tract variables (e.g. tongue body constriction location), but identifying the most appropriate coordinate system for articulatory control remains an open question. In this study, we advance a model in which holistic tongue shape modes represent a potential low-dimensional control basis for a simple dynamical law. We first discover empirical tongue shape modes in a cross-speaker coordinate space and then fit the model to ultrasound data on monophthongal vowels from 36 speakers of British English. A three-dimensional linear point attractor fitted to these time-varying modes recovers the dynamics of tongue shape with a high degree of accuracy. This suggests that complex tongue movement can arise from independent modes that linearly combine under simple dynamical laws, thereby relocating some complexity from the control signal to the coordinate system. We show that this framing explains why one-dimensional articulatory measures can exhibit observable nonlinearities, and hypothesize that shape modes are a plausible kinematic expression of underlying muscle synergies.

Abstract

Speech Processing

Explore similar work

A low-dimensional dynamical basis for tongue shape control

Articulatory strategy as a source of variation in acoustic vowel dynamics

Structured Phonological Representations for Audio-Articulatory rtMRI Speech Classification