# Deep Speech Synthesis from Articulatory Representations

arXiv: https://arxiv.org/abs/2209.06337 · HTML: https://mlsanity.com/paper/2209.06337/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2022.

## Built on by (most cited first, 10 of 10)

- [Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech](https://mlsanity.com/paper/2210.11723/) (2022)
- [Coding Speech through Vocal Tract Kinematics](https://mlsanity.com/paper/2406.12998/) (2024)
- [Self-Supervised Models of Speech Infer Universal Articulatory Kinematics](https://mlsanity.com/paper/2310.10788/) (2023)
- [Articulatory Feature Prediction from Surface EMG during Speech Production](https://mlsanity.com/paper/2505.13814/) (2025)
- [RT-VC: Real-Time Zero-Shot Voice Conversion with Speech Articulatory Coding](https://mlsanity.com/paper/2506.10289/) (2025)
- [Articulation GAN: Unsupervised modeling of articulatory learning](https://mlsanity.com/paper/2210.15173/) (2022)
- [Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP](https://mlsanity.com/paper/2409.02451/) (2024)
- [CiwaGAN: Articulatory information exchange](https://mlsanity.com/paper/2309.07861/) (2023)
- [ARTI-6: Towards Six-dimensional Articulatory Speech Encoding](https://mlsanity.com/paper/2509.21447/) (2025)
- [GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis](https://mlsanity.com/paper/2406.10514/) (2024)

## Abstract (arXiv)

In the articulatory synthesis task, speech is synthesized from input features containing information about the physical behavior of the human vocal tract. This task provides a promising direction for speech synthesis research, as the articulatory space is compact, smooth, and interpretable. Current works have highlighted the potential for deep learning models to perform articulatory synthesis. However, it remains unclear whether these models can achieve the efficiency and fidelity of the human speech production system. To help bridge this gap, we propose a time-domain articulatory synthesis methodology and demonstrate its efficacy with both electromagnetic articulography (EMA) and synthetic articulatory feature inputs. Our model is computationally efficient and achieves a transcription word error rate (WER) of 18.5% for the EMA-to-speech task, yielding an improvement of 11.6% compared to prior work. Through interpolation experiments, we also highlight the generalizability and interpretability of our approach.