声效查询语音模仿微调策略获挑战冠军

精选理由

你同事那篇声效查询微调方案，用语音模仿来操作，和之前方法比效果不同，值得看看。

AI 摘要

该报告介绍了针对AES AIMLA 2025挑战的声效查询方法，通过语音模仿实现。采用两种微调策略，一是冻结预训练CED编码器的对比学习，二是用MobileNetV3编码器的联合对比三元组学习。该报告更新后补充了挑战后公开的详细信息。

原文 · arXiv cs.AI

Finetuning Strategies for Querying Sounds by Vocal Imitation

This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate two complementary fine-tuning strategies: contrastive learning with a frozen, pretrained CED encoder, and joint contrastive-triplet learning with semi-hard negatives using a MobileNetV3 encoder. This report has been updated for posterity to include details released after the challenge.

阅读原文