# Finetuning Strategies for Querying Sounds by Vocal Imitation

arXiv: https://arxiv.org/abs/2608.19174 · HTML: https://mlsanity.com/paper/2608.19174/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 7 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Builds on (most cited first, 2 of 2)

- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining](https://mlsanity.com/paper/2408.11638/) (2024)

## Abstract (arXiv)

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.