Jonathan-Greif/QBV

This repository provides the code for "Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining", presented at DCASE 2024. The paper addresses the challenge of audio retrieval using vocal imitations as queries, proposing a dual encoder architecture that leverages pretrained CNNs and an adapted NT-Xent loss for fine-tuning.

Language: Python - Size: 1.61 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0