# Tracking Articulatory Dynamics in Speech with a Fixed-Weight BiLSTM-CNN Architecture

arXiv: https://arxiv.org/abs/2504.18099 · HTML: https://mlsanity.com/paper/2504.18099/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 25 Apr 2025.

## Builds on (most cited first, 6 of 6)

- [Speech Recognition with no speech or with noisy speech](https://mlsanity.com/paper/1903.00739/) (2019)
- [Speech based Depression Severity Level Classification Using a Multi-Stage Dilated CNN-LSTM Model](https://mlsanity.com/paper/2104.04195/) (2021)
- [Improved acoustic-to-articulatory inversion using representations from pretrained self-supervised learning models](https://mlsanity.com/paper/2210.16871/) (2022)
- [Estimating articulatory movements in speech production with transformer networks](https://mlsanity.com/paper/2104.05017/) (2021)
- [Independent and automatic evaluation of acoustic-to-articulatory inversion models](https://mlsanity.com/paper/1911.06573/) (2019)
- [Acoustic-to-articulatory inversion for dysarthric speech: Are pre-trained self-supervised representations favorable?](https://mlsanity.com/paper/2309.01108/) (2023)

## Abstract (arXiv)

Speech production is a complex sequential process which involve the coordination of various articulatory features. Among them tongue being a highly versatile active articulator responsible for shaping airflow to produce targeted speech sounds that are intellectual, clear, and distinct. This paper presents a novel approach for predicting tongue and lip articulatory features involved in a given speech acoustics using a stacked Bidirectional Long Short-Term Memory (BiLSTM) architecture, combined with a one-dimensional Convolutional Neural Network (CNN) for post-processing with fixed weights initialization. The proposed network is trained with two datasets consisting of simultaneously recorded speech and Electromagnetic Articulography (EMA) datasets, each introducing variations in terms of geographical origin, linguistic characteristics, phonetic diversity, and recording equipment. The performance of the model is assessed in Speaker Dependent (SD), Speaker Independent (SI), corpus dependent (CD) and cross corpus (CC) modes. Experimental results indicate that the proposed model with fixed weights approach outperformed the adaptive weights initialization with in relatively minimal number of training epochs. These findings contribute to the development of robust and efficient models for articulatory feature prediction, paving the way for advancements in speech production research and applications.