From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer
Published 15 Sept 2026arXiv:2609.13260
Updated 29 h ago · first seen 15 Sept 2026
paper_01M2JK0C8S0H32ZJVAMX3Z2JTM
Abstract
This paper proposes SpecAugment-Patch Merging, a simple yet effective method to accelerate Audio Spectrogram Transformer (AST) training. We first apply SpecAugment to mask input spectrograms at the patch level, and after positional embeddings are added, the method selects r pairs of masked patches and merges them, reducing the number of tokens processed by the Transformer. Increasing the number of merged pairs r from 0 to 100 keeps mAP on AudioSet nearly unchanged (34.07 to 34.08) while throughput increases from 43.3 to 49.3 samples/sec, which is a relatively 13.9% improvement. Similar patterns appear on ESC-50 and Speech Commands V2, where throughput steadily improves with only minor accuracy changes, demonstrating that this merging approach provides faster training with minimal performance loss.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 1
- New paperPaperFrom Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer
New paper: From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer
arxiv
Sources
Sources 1
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.