This paper surveys recent advances in brain-to-language decoding, including text generation, personalized speech, and facial animation.
This paper provides a comprehensive synthesis of recent advances in brain-to-language decoding, which is novel compared to prior work that focused on specific aspects of the field.
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
Brain-to-language decoding translates neural activity associated with language production, internal speech and perception into linguistic or expressive outputs. It offers a route to restoring communication after speech loss and a means of studying how the brain represents language. Advances in neural recording and representation learning have expanded the field from constrained recognition and acoustic reconstruction to text generation, streaming personalised speech and facial animation. This survey synthesises these developments across invasive and non-invasive measurements, drawing on a search without a lower year limit and source-led updates through September 2026. We connect Articulated, Inner and Perceived tasks to the neural populations they engage, the representations available to decoders and the outputs those representations can support. We examine model development, public resources and the evolution of evaluation, and compare published performance and communication costs within their reported protocols. The synthesis identifies complementary routes to progress: phonetic, acoustic and semantic targets preserve different aspects of a message; shared representations support reuse across recording conditions and tasks; and online communication increasingly depends on calibration, feedback and user control alongside decoding accuracy. Shared benchmarks enable algorithmic comparisons, while longitudinal studies reveal the demands of sustained use. We discuss these developments and their remaining limitations, then outline a prospective five-level trajectory from commands and language to meaning, scenarios and bidirectional cognitive exchange
Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Tex…
This paper compares the performance of recurrent decoders and selective state-sp…
Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer…
This paper introduces a framework for generating cognitively aligned multi-agent…
From Tokens to Faces: Investigating Discrete Speech Representations for 3D Facial Animation
This paper evaluates four speech representation families for 3D facial synthesis…
SpeechDx: A Multi-Task Benchmark for Clinical Speech AI
Introduces SpeechDx, a large-scale benchmark for clinical speech AI to evaluate…
Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease…
The study investigates the effectiveness of self-supervised learning (SSL) speec…
SLM-SS: Token-Based Speech Separation with Speech Language Models
This paper proposes a token-based generative speech separation framework that mo…
Continuous-Speech Parkinson's Disease Detection Using Acoustic and Inharmonicity Features
This paper proposes a method for identifying Parkinson's disease from continuous…
The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Under…
The paper summarizes the Interspeech2026 Multilingual Conversational Speech Lang…