SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.15053 · 2021

Fine-tuning wav2vec2 for speaker recognition

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence into a fixed-length speaker embedding. To adapt the framework to speaker recognition, we propose a single-utterance classification variant with CE or AAM softmax loss, and an utterance-pair classification variant with BCE loss. Our best performing variant, w2v2-aam, achieves a 1.88% EER on the extended voxceleb1 test set compared to 1.69% EER with an ECAPA-TDNN baseline. Code is available at https://github.com/nikvaessen/w2v2-speaker.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.15053")
get_code_for_paper("2109.15053")
have("2109.15053")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.15053.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.15053.svg)](https://syntology.ai/paper/2109.15053)

Connect an agent — have() is free.