The reviewed record of science sign in
Pith

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

Scaling up masked audio encoder learning for general audio classification

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:4VB2TWEKrecord.jsonopen to challenge →

classification cs.SD eess.AS
keywords audioclassificationdashengspeechenvironmentalmusicencodergeneral
0
0 comments X
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/.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity

    cs.SD 2026-06 unverdicted novelty 8.0

    LambdaMark is the first generic radioactive audio watermark that injects multi-bit messages into semantic latent representations, achieving robustness to distortions and removal attacks even after downstream model finetuning.

  2. FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model

    cs.SD 2026-06 unverdicted novelty 7.0

    FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates l...

  3. ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

    cs.SD 2026-06 unverdicted novelty 5.0

    ALM2Vec learns unified audio embeddings from large audio-language models for text-audio retrieval, instruction-aware retrieval, and other tasks across domains.

  4. From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning

    eess.AS 2026-07 unverdicted novelty 3.0

    A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.