Pith. sign in

REVIEW 4 cited by

Scaling up masked audio encoder learning for general audio classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.06992 v2 pith:4VB2TWEK submitted 2024-06-11 cs.SD eess.AS

Heinrich Dinkel , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang , Bin Wang This is my paper
classification cs.SDeess.AS
keywords audioclassificationdashengspeechenvironmentalmusicencodergeneral
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks, and vice versa. While self-supervised (SSL) audio representations offer an alternative, there has been limited exploration of scaling both model and dataset sizes for SSL-based general audio classification. We introduce Dasheng, a simple SSL audio encoder, based on the efficient masked autoencoder framework. Trained with 1.2 billion parameters on 272,356 hours of diverse audio, Dasheng obtains significant performance gains on the HEAR benchmark. It outperforms previous works on CREMA-D, LibriCount, Speech Commands, VoxLingua, and competes well in music and environment classification. Dasheng features inherently contain rich speech, music, and environmental information, as shown in nearest-neighbor classification experiments. Code is available https://github.com/richermans/dasheng/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Trained connectors and audio-only gated adapters integrate audio into a frozen vision-language embedding space, preserving base outputs bit-exactly and yielding emergent audio-image retrieval.

  2. Large Audio Language Models for Spoofing-Aware Speaker Verification

    cs.SD 2026-07 conditional novelty 6.0 of 10

    Adapted LALMs can reach competitive spoofing-aware speaker verification (89.3% accuracy, 0.19 min a-DCF on an ASVspoof5 subset), though zero-shot performance is near chance.

  3. Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification

    cs.SD 2025-09 conditional novelty 6.0 of 10

    A binarized prototypical probing method that pools per-class evidence from patch tokens substantially outperforms [cls]-token and attentive probes on multi-label audio classification benchmarks.

  4. Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning

    cs.SD 2025-06 conditional novelty 3.0 of 10

    Transferring I-JEPA's masked latent prediction to mel-spectrograms yields competitive audio representations on music and environmental sound tasks with a small fraction of the training data.

Pith tools