Pith. sign in

REVIEW 1 cited by

Federated Self-supervised Speech Representations: Are We There Yet?

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

arxiv 2204.02804 v2 pith:4AI34NYX submitted 2022-04-06 cs.SD cs.LGeess.AS

classification cs.SDcs.LGeess.AS
keywords speechsystemsdataexistingfederatedhardwarelearningrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The ubiquity of microphone-enabled devices has lead to large amounts of unlabelled audio data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of speech representations. In this paper, we provide a first-of-its-kind systematic study of the feasibility and complexities for training speech SSL models under FL scenarios from the perspective of algorithms, hardware, and systems limits. Despite the high potential of their combination, we find existing system constraints and algorithmic behaviour make SSL and FL systems nearly impossible to build today. Yet critically, our results indicate specific performance bottlenecks and research opportunities that would allow this situation to be reversed. While our analysis suggests that, given existing trends in hardware, hybrid SSL and FL speech systems will not be viable until 2027. We believe this study can act as a roadmap to accelerate work towards reaching this milestone much earlier.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies

    cs.CL 2026-07 conditional novelty 4.0 of 10

    A SpeechLLM-based ASR system can be fine-tuned with federated learning and LoRA adapters, reaching word error rates close to centralized training on English and Italian while transmitting only a small fraction of the model.

Pith tools