# NAPE：下一补丁嵌入预测实现可扩展音频学习器

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-20 08:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmt2o0smc01ltro6two10xi3e
- 原文链接：https://arxiv.org/abs/2608.19863

## AI 摘要

NAPE提出极简自监督框架，用因果Transformer从先前补丁预测log-mel频谱图的下一补丁嵌入，仅靠因果掩码和停止梯度作为训练信号，无需重建解码器、声学tokenizer或师生架构。在六项音频与语音基准上，NAPE在多项任务取得最优微调性能，跨编码器规模扩展一致，并展现强线性探测结果与结构化注意力模式。

## 正文

Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance. A markedly different pre-training philosophy underpins the most influential progress in language modeling and, more recently, in visual representation learning: rather than train encoders as static feature extractors, models are trained to predict the next element, a discrete token or a continuous embedding, from the preceding context. Autoregressive prediction thereby provides a unified pre-training interface that transfers across modalities, compelling the model to learn the underlying data distribution. We ask whether such a simple causal paradigm can yield strong audio learners, given that audio's temporal structure makes autoregressive prediction of patch embeddings a natural fit. We introduce NAPE (Next-Audio-Patch-Embedding prediction), a self-supervised framework in which a causal Transformer predicts each next patch embedding of a log-mel spectrogram from the previous ones, using causal masking and stop-gradient as its sole training signal. The design is intentionally minimalist, avoiding reconstruction decoders, acoustic tokenizers, student-teacher setups, and auxiliary regularization losses. Across six audio and speech benchmarks, NAPE achieves state-of-the-art fine-tuning performance on several tasks, scales consistently across encoder sizes, and yields strong linear-probing results. NAPE also produces structured attention patterns without explicit supervision.