Picture for Florian Schmid

Florian Schmid

Effective Pre-Training of Audio Transformers for Sound Event Detection

Add code
Sep 14, 2024
Figure 1 for Effective Pre-Training of Audio Transformers for Sound Event Detection
Figure 2 for Effective Pre-Training of Audio Transformers for Sound Event Detection
Figure 3 for Effective Pre-Training of Audio Transformers for Sound Event Detection
Viaarxiv icon

Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining

Add code
Aug 21, 2024
Viaarxiv icon

Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval

Add code
Aug 21, 2024
Viaarxiv icon

Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets

Add code
Jul 17, 2024
Viaarxiv icon

Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge

Add code
May 16, 2024
Viaarxiv icon

Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models

Add code
Oct 24, 2023
Viaarxiv icon

Device-Robust Acoustic Scene Classification via Impulse Response Augmentation

Add code
May 12, 2023
Viaarxiv icon

Low-Complexity Audio Embedding Extractors

Add code
Mar 03, 2023
Viaarxiv icon

Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers

Add code
Nov 25, 2022
Viaarxiv icon

Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation

Add code
Nov 09, 2022
Viaarxiv icon