audio-learning

Tag

Cards List
#audio-learning

Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners

Hugging Face Daily Papers ↗ · 2026-08-20 Cached

NAPE is a self-supervised audio learning framework that uses causal Transformers to predict next spectrogram patch embeddings, achieving state-of-the-art performance on multiple audio and speech benchmarks with a minimalist design.

0 favorites 0 likes
← Back to home

Submit Feedback