Speech brain–computer interfaces for communication rehabilitation: State-of-the-art decoding models, clinical applications, and ethical challenges

Abstract

Speech brain–computer interfaces (BCIs) represent an interdisciplinary neural engineering innovation enabling communication rehabilitation for individuals with anarthria or severe dysarthria. By decoding cortical activity into text or synthetic speech via nonmuscular pathways, this technology provides critical communication alternatives for patients with amyotrophic lateral sclerosis, poststroke aphasia, or locked-in syndrome. Since early demonstrations of computer cursor control, significant advancements have been achieved in real-time decoding of limited lexical sets, though challenges persist in system compatibility, decoding accuracy, transmission speed, and ethical governance. This review systematically evaluates state-of-the-art speech decoding models, describes recent technological breakthroughs, and identifies unresolved challenges in clinical translation, while assessing cross-disciplinary applications of speech BCIs in healthcare and assistive technologies.

Keywords

clinical translation / decoding cortical activity / healthcare and assistive technologies / speech brain-computer interfaces (BCIs) / speech decoding models

References

[1] Boschi V, Catricalà E, Consonni M, Chesi C, Moro A, Cappa SF. Connected speech in neurodegenerative language disorders: a review. Front Psychol. 2017; 8:269. https://doi.org/10.3389/fpsyg.2017.00269

[2] Stavisky SD. Restoring speech using brain-computer interfaces. Annu Rev Biomed Eng. 2025; 27(1): 29-54. https://doi.org/10.1146/annurev-bioeng-110122-012818

[3] Schalk G, Leuthardt EC. Brain-computer interfaces using electrocorticographic signals. IEEE Rev Biomed Eng. 2011; 4: 140-154. https://doi.org/10.1109/RBME.2011.2172408

[4] Kennedy PR, Bakay RA. Restoration of neural output from a paralyzed patient by a direct brain connection. Neuroreport. 1998; 9(8): 1707-1711. https://doi.org/10.1097/00001756-199806010-00007

[5] McFarland DJ, Wolpaw JR. EEG-based brain-computer interfaces. Curr Opin Biomed Eng. 2017; 4: 194-200. https://doi.org/10.1016/j.cobme.2017.11.004

[6] Abiri R, Borhani S, Sellers EW, Jiang Y, Zhao X. A comprehensive review of EEG-based brain-computer interface paradigms. J Neural Eng. 2019; 16(1):011001. https://doi.org/10.1088/1741-2552/aaf12e

[7] Leuthardt EC, Schalk G, Wolpaw JR, Ojemann JG, Moran DW. A brain-computer interface using electrocorticographic signals in humans. J Neural Eng. 2004; 1(2): 63-71. https://doi.org/10.1088/1741-2560/1/2/001

[8] Pasley BN, David SV, Mesgarani N, et al. Reconstructing speech from human auditory cortex. PLoS Biol. 2012; 10(1):e1001251. https://doi.org/10.1371/journal.pbio.1001251

[9] Lotte F, Bougrain L, Cichocki A, et al. A review of classification algorithms for EEG-based brain-computer interfaces: a 10 year update. J Neural Eng. 2018; 15(3):031005. https://doi.org/10.1088/1741-2552/aab2f2

[10] Anumanchipalli GK, Chartier J, Chang EF. Speech synthesis from neural decoding of spoken sentences. Nature. 2019; 568(7753): 493-498. https://doi.org/10.1038/s41586-019-1119-1

[11] Metzger SL, Littlejohn KT, Silva AB, et al. A high-performance neuroprosthesis for speech decoding and avatar control. Nature. 2023; 620(7976): 1037-1046. https://doi.org/10.1038/s41586-023-06443-4

[12] Willett FR, Avansino DT, Hochberg LR, Henderson JM, Shenoy KV. High-performance brain-to-text communication via handwriting. Nature. 2021; 593(7858): 249-254. https://doi.org/10.1038/s41586-021-03506-2

[13] Moses DA, Leonard MK, Makin JG, Chang EF. Real-time decoding of question-and-answer speech dialogue using human cortical activity. Nat Commun. 2019; 10(1):3096. https://doi.org/10.1038/s41467-019-10994-4

[14] Pandarinath C, Nuyujukian P, Blabe CH, et al. High performance communication by people with paralysis using an intracortical brain-computer interface. eLife. 2017; 6:e18554. https://doi.org/10.7554/eLife.18554

[15] Card NS, Wairagkar M, Iacobacci C, et al. An accurate and rapidly calibrating speech neuroprosthesis. N Engl J Med. 2024; 391(7): 609-618. https://doi.org/10.1056/NEJMoa2314132

[16] Angrick M, Luo S, Rabbani Q, et al. Online speech synthesis using a chronically implanted brain–computer interface in an individual with ALS. Sci Rep. 2024; 14(1):9617. https://doi.org/10.1038/s41598-024-60277-2

[17] Zeng Y, Sun K, Lu E. Declaration on the ethics of brain-computer interfaces and augment intelligence. AI Ethics. 2021; 1(3): 209-211. https://doi.org/10.1007/s43681-020-00036-x

[18] Mridha MF, Das SC, Kabir MM, Lima AA, Islam MR, Watanobe Y. Brain-computer interface: advancement and challenges. Sensors. 2021; 21(17):5746. https://doi.org/10.3390/s21175746

[19] Edelman BJ, Zhang S, Schalk G, et al. Non-invasive brain-computer interfaces: state of the art and trends. IEEE Rev Biomed Eng. 2025; 18: 26-49. https://doi.org/10.1109/rbme.2024.3449790

[20] Zhang H, Jiao L, Yang S, et al. Brain-computer interfaces: the innovative key to unlocking neurological conditions. Int J Surg. 2024; 110(9): 5745-5762. https://doi.org/10.1097/js9.0000000000002022

[21] Pitt KM, Brumberg JS, Burnison JD, Mehta J, Kidwai J. Behind the scenes of noninvasive brain-computer interfaces: a review of electroencephalography signals, how they are recorded, and why they matter. Perspect ASHA Spec Interest Groups. 2019; 4(6): 1622-1636. https://doi.org/10.1044/2019_pers-19-00059

[22] Volkova K, Lebedev MA, Kaplan A, Ossadtchi A. Decoding movement from electrocorticographic activity: a review. Front Neuroinf. 2019; 13:74. https://doi.org/10.3389/fninf.2019.00074

[23] Waldert S. Invasive vs. non-invasive neuronal signals for brain-machine interfaces: will one prevail? Front Neurosci. 2016; 10:295. https://doi.org/10.3389/fnins.2016.00295

[24] Zhao ZP, Nie C, Jiang CT, et al. Modulating brain activity with invasive brain-computer interface: a narrative review. Brain Sci. 2023; 13(1):134. https://doi.org/10.3390/brainsci13010134

[25] Martin S, Brunner P, Iturrate I, et al. Word pair classification during imagined speech using direct brain recordings. Sci Rep. 2016; 6(1):25803. https://doi.org/10.1038/srep25803

[26] Panachakel JT, Ramakrishnan AG. Decoding covert speech from EEG: a comprehensive review. Front Neurosci. 2021; 15:642251. https://doi.org/10.3389/fnins.2021.642251

[27] Luo S, Rabbani Q, Crone NE. Brain-computer interface: applications to speech decoding and synthesis to augment communication. Neurotherapeutics. 2022; 19(1): 263-273. https://doi.org/10.1007/s13311-022-01190-2

[28] Guenther FH, Brumberg JS, Wright EJ, et al. A wireless brain-machine interface for real-time speech synthesis. PLoS One. 2009; 4(12):e8218. https://doi.org/10.1371/journal.pone.0008218

[29] Birbaumer N, Gallegos-Ayala G, Wildgruber M, Silvoni S, Soekadar SR. Direct brain control and communication in paralysis. Brain Topogr. 2014; 27(1): 4-11. https://doi.org/10.1007/s10548-013-0282-1

[30] Chaudhary U, Xia B, Silvoni S, Cohen LG, Birbaumer N. Brain-computer interface-based communication in the completely locked-in state. PLoS Biol. 2017; 15(1):e1002593. https://doi.org/10.1371/journal.pbio.1002593

[31] Kellis S, Miller K, Thomson K, Brown R, House P, Greger B. Decoding spoken words using local field potentials recorded from the cortical surface. J Neural Eng. 2010; 7(5):056007. https://doi.org/10.1088/1741-2560/7/5/056007

[32] Herff C, Heger D, de Pesters A, et al. Brain-to-text: decoding spoken phrases from phone representations in the brain. Front Neurosci. 2015; 9:217. https://doi.org/10.3389/fnins.2015.00217

[33] Herff C, Schultz T. Automatic speech recognition from neural signals: a focused review. Front Neurosci. 2016; 10: 532. https://doi.org/10.3389/fnins.2016.00429

[34] Lotte F, Brumberg JS, Brunner P, et al. Electrocorticographic representations of segmental features in continuous speech. Front Hum Neurosci. 2015; 9:97. https://doi.org/10.3389/fnhum.2015.00097

[35] Chakrabarti S, Sandberg H, Brumberg J, Krusienski DJ. Progress in speech decoding from the electrocorticogram. Biomed Eng Lett. 2015; 5(1): 10-21. https://doi.org/10.1007/s13534-015-0175-1

[36] Makin JG, Moses DA, Chang EF. Machine translation of cortical activity to text with an encoder-decoder framework. Nat Neurosci. 2020; 23(4): 575-582. https://doi.org/10.1038/s41593-020-0608-8

[37] Luo S, Angrick M, Coogan C, et al. Stable decoding from a speech BCI enables control for an individual with ALS without recalibration for 3 months. Adv Sci. 2023; 10(35):e2304853. https://doi.org/10.1002/advs.202304853

[38] Iljina O, Derix J, Schirrmeister RT, et al. Neurolinguistic and machine-learning perspectives on direct speech BCIs for restoration of naturalistic communication. Brain-Comput Interfaces. 2017; 4(3): 186-199. https://doi.org/10.1080/2326263X.2017.1330611

[39] Vigneau M, Beaucousin V, Hervé PY, et al. Meta-analyzing left hemisphere language areas: phonology, semantics, and sentence processing. Neuroimage. 2006; 30(4): 1414-1432. https://doi.org/10.1016/j.neuroimage.2005.11.002

[40] Rahman N, Khan DM, Masroor K, Arshad M, Rafiq A, Fahim SM. Advances in brain-computer interface for decoding speech imagery from EEG signals: a systematic review. Cogn Neurodyn. 2024; 18(6): 3565-3583. https://doi.org/10.1007/s11571-024-10167-0

[41] Ng HW, Guan C. Subject-independent meta-learning framework towards optimal training of EEG-based classifiers. Neural Netw. 2024; 172:106108. https://doi.org/10.1016/j.neunet.2024.106108

[42] Soroush PZ, Herff C, Ries SK, Shih JJ, Schultz T, Krusienski DJ. The nested hierarchy of overt, mouthed, and imagined speech activity evident in intracranial recordings. Neuroimage. 2023; 269:119913. https://doi.org/10.1016/j.neuroimage.2023.119913

[43] Wang Y, Zhang M, Wu R, et al. Silent speech decoding using spectrogram features based on neuromuscular activities. Brain Sci. 2020; 10(7):442. https://doi.org/10.3390/brainsci10070442

[44] Chen X, Zhang X, Chen X, Chen X. Decoding silent speech based on high-density surface electromyogram using spatiotemporal neural network. IEEE Trans Neural Syst Rehabil Eng. 2023; 31: 2441-2452. https://doi.org/10.1109/TNSRE.2023.3266299

[45] Varshney Y, Khan A. Imagined speech classification using six phonetically distributed words. Front Signal Process. 2022; 2:760643. https://doi.org/10.3389/frsip.2022.760643

[46] Schieber MH. Constraints on somatotopic organization in the primary motor cortex. J Neurophysiol. 2001; 86(5): 2125-2143. https://doi.org/10.1152/jn.2001.86.5.2125

[47] Thomas TM, Singh A, Bullock LP, et al. Decoding articulatory and phonetic components of naturalistic continuous speech from the distributed language network. J Neural Eng. 2023; 20(4):046030. https://doi.org/10.1088/1741-2552/ace9fb

[48] Cho CJ, Wu P, Prabhune TS, Agarwal D, Anumanchipalli GK. Coding speech through vocal tract kinematics. IEEE J Sel Top Signal Process. 2024; 18(8): 1427-1440. https://doi.org/10.1109/jstsp.2024.3497655

[49] Bocquelet F, Hueber T, Girin L, Savariaux C, Yvert B. Real-time control of an articulatory-based speech synthesizer for brain-computer interfaces. PLoS Comput Biol. 2016; 12(11):e1005119. https://doi.org/10.1371/journal.pcbi.1005119

[50] Favero P, Berezutskaya J, Ramsey NF, Nazarov A, Freudenburg ZV. Mapping acoustics to articulatory gestures in dutch: relating speech gestures, acoustics and neural data. Annu Int Conf IEEE Eng Med Biol Soc. 2022; 2022:802806-806. https://doi.org/10.1109/embc48229.2022.9871909

[51] Oohashi H, Watanabe H, Taga G. Acquisition of vowel articulation in childhood investigated by acoustic-to-articulatory inversion. Infant Behav Dev. 2017; 46: 178-193. https://doi.org/10.1016/j.infbeh.2017.01.007

[52] Ibayashi K, Kunii N, Matsuo T, et al. Decoding speech with integrated hybrid signals recorded from the human ventral motor cortex. Front Neurosci. 2018; 12:221. https://doi.org/10.3389/fnins.2018.00221

[53] Chartier J, Anumanchipalli GK, Johnson K, Chang EF. Encoding of articulatory kinematic trajectories in human speech sensorimotor cortex. Neuron. 2018; 98(5):1042-54.e4. https://doi.org/10.1016/j.neuron.2018.04.031

[54] Dichter BK, Breshears JD, Leonard MK, Chang EF. The control of vocal pitch in human laryngeal motor cortex. Cell. 2018; 174(1): 21-31.e9. https://doi.org/10.1016/j.cell.2018.05.016

[55] Octave E, Mikolaj K, Chananel B, Antonio Elia F, Tobias R. Decoding of selective attention to continuous speech from the human auditory brainstem response. Neuroimage. 2019; 200: 1-11. https://doi.org/10.1016/j.neuroimage.2019.06.029

[56] Angrick M, Herff C, Mugler E, et al. Speech synthesis from ECoG using densely connected 3D convolutional neural networks. J Neural Eng. 2019; 16(3):036019. https://doi.org/10.1088/1741-2552/ab0c59

[57] Moses DA, Metzger SL, Liu JR, et al. Neuroprosthesis for decoding speech in a paralyzed person with anarthria. N Engl J Med. 2021; 385(3): 217-227. https://doi.org/10.1056/NEJMoa2027540

[58] Petrosyan A, Voskoboinikov A, Sukhinin D, et al. Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network. J Neural Eng. 2022; 19(6):066001. https://doi.org/10.1088/1741-2552/aca1e1

[59] Willett FR, Kunz EM, Fan C, et al. A high-performance speech neuroprosthesis. Nature. 2023; 620(7976): 1031-1036. https://doi.org/10.1038/s41586-023-06377-x

[60] Chen X, Wang R, Khalilian-Gourtani A, et al. A neural speech decoding framework leveraging deep learning and speech synthesis. Nat Mach Intell. 2024; 6(4): 467-480. https://doi.org/10.1038/s42256-024-00824-8

[61] Wandelt SK, Bjånes DA, Pejsa K, Lee B, Liu C, Andersen RA. Representation of internal speech by single neurons in human supramarginal gyrus. Nat Hum Behav. 2024; 8(6): 1136-1149. https://doi.org/10.1038/s41562-024-01867-y

[62] Wang YT, Wang Y, Jung TP. A cell-phone-based brain-computer interface for communication in daily life. J Neural Eng. 2011; 8(2):025018. https://doi.org/10.1088/1741-2560/8/2/025018

[63] Drăgoi MV, Nisipeanu I, Frimu A, et al. Real-time home automation system using BCI technology. Biomimetics. 2024; 9(10):594. https://doi.org/10.3390/biomimetics9100594

[64] Kaongoen N, Choi J, Jo S. A novel online BCI system using speech imagery and ear-EEG for home appliances control. Comput Methods Programs Biomed. 2022; 224:107022. https://doi.org/10.1016/j.cmpb.2022.107022

[65] Braun JM, Fauth M, Berger M, et al. A brain machine interface framework for exploring proactive control of smart environments. Sci Rep. 2024; 14(1):11054. https://doi.org/10.1038/s41598-024-60280-7

[66] Young MJ, Lin DJ, Hochberg LR. Brain-computer interfaces in neurorecovery and neurorehabilitation. Semin Neurol. 2021; 41(2): 206-216. https://doi.org/10.1055/s-0041-1725137

[67] Pirasteh A, Shamseini Ghiyasvand M, Pouladian M. EEG-based brain-computer interface methods with the aim of rehabilitating advanced stage ALS patients. Disabil Rehabil Assist Technol. 2024; 19(8): 3183-3193. https://doi.org/10.1080/17483107.2024.2316312

[68] Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM. Brain-computer interfaces for communication and control. Clin Neurophysiol. 2002; 113(6): 767-791. https://doi.org/10.1016/s1388-2457(02)00057-3

[69] Mane R, Chouhan T, Guan C. BCI for stroke rehabilitation: motor and beyond. J Neural Eng. 2020; 17(4):041001. https://doi.org/10.1088/1741-2552/aba162

[70] Rabbani Q, Milsap G, Crone NE. The potential for a speech brain-computer interface using chronic electrocorticography. Neurotherapeutics. 2019; 16(1): 144-165. https://doi.org/10.1007/s13311-018-00692-2

[71] Burwell S, Sample M, Racine E. Ethical aspects of brain computer interfaces: a scoping review. BMC Med Ethics. 2017; 18(1): 60. https://doi.org/10.1186/s12910-017-0220-y

[72] Soekadar SR, Birbaumer N, Slutzky MW, Cohen LG. Brain-machine interfaces in neurorehabilitation of stroke. Neurobiol Dis. 2015; 83: 172-179. https://doi.org/10.1016/j.nbd.2014.11.025

[73] Mane R, Wu Z, Wang D. Poststroke motor, cognitive and speech rehabilitation with brain-computer interface: a perspective review. Stroke Vasc Neurol. 2022; 7(6): 541-549. https://doi.org/10.1136/svn-2022-001506

[74] Musso M, Hübner D, Schwarzkopf S, et al. Aphasia recovery by language training using a brain-computer interface: a proof-of-concept study. Brain Commun. 2022; 4(1):fcac008. https://doi.org/10.1093/braincomms/fcac008

[75] Kerous B, Skola F, Liarokapis F. EEG-based BCI and video games: a progress report. Virtual Real. 2018; 22(2): 119-135. https://doi.org/10.1007/s10055-017-0328-x

[76] Stein A, Yotam Y, Puzis R, Shani G, Taieb-Maimon M. EEG-triggered dynamic difficulty adjustment for multiplayer games. Entertain Comput. 2018; 25: 14-25. https://doi.org/10.1016/j.entcom.2017.11.003

[77] Zhang Z, Chen Y, Zhao X, et al. A review of ethical considerations for the medical applications of brain-computer interfaces. Cogn Neurodyn. 2024; 18(6): 3603-3614. https://doi.org/10.1007/s11571-024-10144-7

[78] Hong K.-S, Khan MJ. Hybrid brain-computer interface techniques for improved classification accuracy and increased number of commands: a review. Front Neurorobot. 2017; 11:35. https://doi.org/10.3389/fnbot.2017.00035

[79] Singh A, Thomas T, Li J, Hickok G, Pitkow X, Tandon N. Transfer learning via distributed brain recordings enables reliable speech decoding. Nat Commun. 2025; 16(1):8749. https://doi.org/10.1038/s41467-025-63825-0

[80] Silva AB, Liu JR, Metzger SL, et al. A bilingual speech neuroprosthesis driven by cortical articulatory representations shared between languages. Nat Biomed Eng. 2024; 8(8): 977-991. https://doi.org/10.1038/s41551-024-01207-5

RIGHTS & PERMISSIONS

2025 The Author(s). Journal of Intelligent Medicine published by John Wiley & Sons Australia, Ltd on behalf of Tianjin University.