用外部音频库检索匹配语音，提升脑信号语音检测精度。
Bypassing Direct Reconstruction: Speech Detection from MEG via Large-Scale Audio Retrieval
- 通过对比学习从海量音频中检索最匹配的语音片段
- 在测试集上实现0.962的F1分数，优于直接重建方法
- 适合关注脑机接口与音频检索融合的科研人员
从非侵入式脑信号解码语音极具挑战性。针对LibriBrain 2025语音检测任务，我们提出一种两阶段新框架，跳过直接重建。首先，利用对比学习模型从大规模音频库LibriVox中检索与测试MEG信号最匹配的语音段；其次，基于检索到的音频，直接生成二值化的静音/语音序列。该方法使团队Sherlock Holmes在扩展赛道中取得第一，F1分数达0.962，证明利用外部音频数据库是高效可行的策略。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。