From Neurons to Conversation: Speech Brain-Computer Interfaces
Abstract
Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative intent into external outputs such as text, synthesized voice, or avatar control. Recent advances in intracortical and electrocorticographic recording, deep sequence models, and language-model-assisted decoding have enabled rapid progress, including high-performance attempted-speech decoding and increasingly naturalistic speech synthesis. Yet these achievements also reveal that speech BCIs are not simply neural-to-text decoders. They are adaptive clinical systems in which neural representations, recording hardware, decoding architectures, language priors, feedback, and user learning interact over time. Here, we synthesize speech BCI research from a system-level perspective. We first examine the neural substrates of speech and language, emphasizing their hierarchical, distributed, temporally structured, and non-stationary organization. We then examine recording and decoding choices, closed-loop adaptation, evaluation, clinical translation, and ethics. Across these domains, we highlight recurring trade-offs between signal resolution and invasiveness, low-level motor and high-level semantic targets, decoder accuracy and user agency, and language-model fluency and faithful neural evidence. We argue the next generation of speech BCIs should be evaluated not only by offline accuracy, but also by robustness across sessions, calibration burden, latency, uncertainty, usability, and safeguards against unintended decoding. By reframing speech BCIs as adaptive, user-centred systems, we outline the interdisciplinary priorities spanning speech neuroscience, neural engineering, machine learning, clinical practice, and neuroethics needed to move from proof-of-concept decoding toward reliable, expressive, and controllable communication neuroprostheses.
Related
- A Common Measure of Communication for Speech Brain-Computer Interfaces
- Human learning of noninvasive brain–computer interfaces via manifold geometry
- Real-time noise cancellation for EEG monitoring and brain-computer interfaces
- Large language models integrated into brain–computer interfaces for communication and control: a systematic review
- Regulating Next-Generation Implantable Brain-Computer Interfaces: Recommendations for Ethical Development and Implementation
BibTeX
@misc{khajehnejad2026from,
title = {{From Neurons to Conversation: Speech Brain-Computer Interfaces}},
author = {Moein Khajehnejad and Forough Habibollahi and Tommaso Boccato and Margarida Sousa and Michal Olak and Francesco Jamal Sheiban and Matteo Ferrante},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36736},
eprint = {2609.36736},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36736},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - From Neurons to Conversation: Speech Brain-Computer Interfaces
AU - Moein Khajehnejad
AU - Forough Habibollahi
AU - Tommaso Boccato
AU - Margarida Sousa
AU - Michal Olak
AU - Francesco Jamal Sheiban
AU - Matteo Ferrante
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36736
UR - https://arxiv.org/abs/2609.36736
AB - Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative intent into external outputs such as text, synthesized voice, or avatar control. Recent advances in intracortical and electrocorticographic recording, deep sequence models, and language-model-assisted decoding have enabled rapid progress, including high-performance attempted-speech decoding and increasingly naturalistic speech synthesis. Yet these achievements also reveal that speech BCIs are not simply neural-to-text decoders. They are adaptive clinical systems in which neural representations, recording hardware, decoding architectures, language priors, feedback, and user learning interact over time. Here, we synthesize speech BCI research from a system-level perspective. We first examine the neural substrates of speech and language, emphasizing their hierarchical, distributed, temporally structured, and non-stationary organization. We then examine recording and decoding choices, closed-loop adaptation, evaluation, clinical translation, and ethics. Across these domains, we highlight recurring trade-offs between signal resolution and invasiveness, low-level motor and high-level semantic targets, decoder accuracy and user agency, and language-model fluency and faithful neural evidence. We argue the next generation of speech BCIs should be evaluated not only by offline accuracy, but also by robustness across sessions, calibration burden, latency, uncertainty, usability, and safeguards against unintended decoding. By reframing speech BCIs as adaptive, user-centred systems, we outline the interdisciplinary priorities spanning speech neuroscience, neural engineering, machine learning, clinical practice, and neuroethics needed to move from proof-of-concept decoding toward reliable, expressive, and controllable communication neuroprostheses.
ER -