Pith. sign in

REVIEW

Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification

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 2309.14838 v2 pith:VLKEJ77V submitted 2023-09-26 cs.SD eess.AS

classification cs.SDeess.AS
keywords knowledgenon-targetspeakerautomaticspeakersverificationconventionaldistillation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the conventional label-level KD overlooks the significant knowledge from non-target speakers, particularly their classification probabilities, which can be crucial for automatic speaker verification. In this paper, we first demonstrate that leveraging a larger number of training non-target speakers improves the performance of automatic speaker verification models. Inspired by this finding about the importance of non-target speakers' knowledge, we modified the conventional label-level KD by disentangling and emphasizing the classification probabilities of non-target speakers during knowledge distillation. The proposed method is applied to three different student model architectures and achieves an average of 13.67% improvement in EER on the VoxCeleb dataset compared to embedding-level and conventional label-level KD methods.

Discussion (0). Continue with ORCID to comment.

Pith tools