arXiv Computation and Language

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

arXiv AI
Aug 20

Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings

Brain2Qwerty v2 is a model that decodes natural sentences from real‑time magnetoencephalography (MEG) recordings, achieving an average word error rate of 39% across 22,000 sentences typed by nine subjects. The model uses character, word, and sentence‑level representations and shows that decoding accuracy improves log‑linearly with more data, narrowing the gap to intracranial brain‑computer interfaces. AI contributes by replacing hand‑crafted event detection with deep learning, fine‑tuning large language models for semantic extraction, and employing AI agents to refine the decoding pipeline through automated code development.

By Mingfang Zhang, Jarod L\'evy, Cedric Rommel, J\'er\'emy Rapin, Corentin Bel, Julie Bonnaire, Daniel Nieto, Pierre Bourdillon, Svetlana Pinet, St\'ephane d'Ascoli, Thomas Moreau, Jean-R\'emi King
arXiv Machine Learning
Aug 27

LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale

LibriBrain100 is a new large‑scale MEG dataset for speech decoding that contains over 100 hours of high‑quality recordings while subjects listened to naturalistic continuous speech. The dataset more than doubles the size of the original LibriBrain release, with a record 80 hours from a single subject and additional 40‑minute recordings from 32 subjects. The authors demonstrate the value of deep within‑subject data and broad multi‑subject data by achieving state‑of‑the‑art word‑classification performance and showing that supervised fine‑tuning can compensate for limited per‑subject data, all supported by open‑source tools and a public competition leaderboard.

By Francesco Mantegna, Dulhan Jayalath, Gereon Elvers, Tasha Kim, Benjamin Ballyk, Alex Fung, SungJun Cho, Teyun Kwon, Luisa Kurth, Miran \"Ozdogan, Gilad Landau, Pratik Somaiya, Natalie Voets, Mark Woolrich, Oiwi Parker Jones
arXiv Machine Learning
Aug 19

Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence

The paper introduces MD‑SigLIP, a margin‑regularized structured semantic alignment framework that directly aligns brain embeddings with text embeddings in a shared semantic space for retrieval‑based decoding. It builds on duplicate‑aware sigmoid contrastive learning and adds a listwise margin‑regularized term to enforce structured ranking constraints between positive semantic clusters and negative samples. Experiments show that this approach achieves state‑of‑the‑art retrieval performance in both full‑vocabulary and subset evaluation settings.

By Jiaqi Wang, Huawen Hu, Shu Zhang
arXiv Computation and Language
5d ago

Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data

The paper introduces a context‑aware neural grapheme‑to‑phoneme (G2P) system for unsegmented languages like Japanese, using a discriminative conditional random field over a word lattice built from dictionaries. It addresses data scarcity by generating over two million sentences with large language models. Experiments show the method surpasses traditional morphological analyzers and neural sequence models, achieving 99.62% target word reading accuracy and very low phoneme error rates on the Joyo‑Kanji‑Yomi benchmark.

By Rui Hu, Zhenpeng Zhan, Xiaolong Lin
arXiv AI
Aug 25

Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings

The paper introduces a Cross-Subject Perceived Speech Decoding (CPSD) framework that tackles the challenge of decoding perceived speech from non‑invasive brain recordings across different subjects. CPSD uses a two‑stage training process: first, contrastive learning pre‑trains a source model on multiple subjects to capture shared representations; second, personal specialization fine‑tunes the model for a target subject by extracting consistent components and further training on that subject’s data. A Positional Encoding‑based Spatial Attention (PESA) module is added to remap MEG/EEG data into a standardized reference space, improving cross‑subject consistency. Evaluations on three datasets (Armeni 2022, PKUEEG 2025, Broderick 2018) show that CPSD outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top‑10 accuracy, demonstrating its effectiveness, efficiency, and robustness.

By Aoke Zhang, Bo Wang, Xihong Wu, Heping Cheng, Jing Chen
Hugging Face Trending Papers
Jun 24

From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models

Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes.