Pith. sign in

REVIEW

End-to-end streaming model for low-latency speech anonymization

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 2406.09277 v2 pith:RBATG3LR submitted 2024-06-13 eess.AS cs.CLcs.LG

classification eess.AScs.CLcs.LG
keywords speakeranonymizationencoderlatencymodelstreamingachievescontent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To address these concerns, we propose a streaming model that achieves speaker anonymization with low latency. The system is trained in an end-to-end autoencoder fashion using a lightweight content encoder that extracts HuBERT-like information, a pretrained speaker encoder that extract speaker identity, and a variance encoder that injects pitch and energy information. These three disentangled representations are fed to a decoder that re-synthesizes the speech signal. We present evaluation results from two implementations of our system, a full model that achieves a latency of 230ms, and a lite version (0.1x in size) that further reduces latency to 66ms while maintaining state-of-the-art performance in naturalness, intelligibility, and privacy preservation.

Discussion (0). Continue with ORCID to comment.

Pith tools