Saved in:
Bibliographic Details
Main Authors: Xiao, Boda, Wang, Bo, Cheng, Heping
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13099
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911679597510656
author Xiao, Boda
Wang, Bo
Cheng, Heping
author_facet Xiao, Boda
Wang, Bo
Cheng, Heping
contents Decoding speech from non-invasive brain signals is challenging. For the LibriBrain 2025 Speech Detection task, we propose a novel two-step framework that bypasses direct reconstruction. First, a contrastive learning model retrieves the matching speech segment for the given test MEG from a large-scale audio library (LibriVox). Second, a speech detection model generates the binary silence/speech sequence directly from this retrieved audio. With this approach, our team Sherlock Holmes achieved first place in the extended track (F1-score: 0.962), demonstrating that leveraging external audio databases is a highly effective strategy.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13099
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bypassing Direct Reconstruction: Speech Detection from MEG via Large-Scale Audio Retrieval
Xiao, Boda
Wang, Bo
Cheng, Heping
Sound
Decoding speech from non-invasive brain signals is challenging. For the LibriBrain 2025 Speech Detection task, we propose a novel two-step framework that bypasses direct reconstruction. First, a contrastive learning model retrieves the matching speech segment for the given test MEG from a large-scale audio library (LibriVox). Second, a speech detection model generates the binary silence/speech sequence directly from this retrieved audio. With this approach, our team Sherlock Holmes achieved first place in the extended track (F1-score: 0.962), demonstrating that leveraging external audio databases is a highly effective strategy.
title Bypassing Direct Reconstruction: Speech Detection from MEG via Large-Scale Audio Retrieval
topic Sound
url https://arxiv.org/abs/2605.13099