REVIEW 3 cited by
USAD: Universal Speech and Audio Representation via Distillation
Not yet reviewed by Pith; the record is open.
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
USAD: Universal Speech and Audio Representation via Distillation
read the original abstract
Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a unified approach to audio representation learning that integrates diverse audio types - speech, sound, and music - into a single model. USAD employs efficient layer-to-layer distillation from domain-specific SSL models to train a student on a comprehensive audio dataset. USAD offers competitive performance across various benchmarks and datasets, including frame and instance-level speech processing tasks, audio tagging, and sound classification, achieving near state-of-the-art results with a single encoder on SUPERB and HEAR benchmarks.
Forward citations
Cited by 3 Pith papers
-
Stage-adaptive audio diffusion modeling
A semantic progress signal from SSL discrepancy slope enables three stage-aware mechanisms that improve training efficiency and performance in audio diffusion models over static baselines.
-
Alethia: A Foundational Encoder for Voice Deepfakes
Alethia is a pretrained audio encoder using continuous embedding prediction and generative flow-matching reconstruction that outperforms existing speech foundation models on voice deepfake tasks with better robustness...
-
SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
SPEAR unifies speech and audio self-supervised learning by masked prediction of multi-codebook tokens distilled from two domain teachers, beating WavLM Large on 12 of 15 SUPERB tasks and scoring competitively on HEAR.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.