Deep Metric Learning for Music Information Retrieval ...
Μ.Δ.Ε. 94 ... : This master thesis explores the application of Deep Metric Learning (DML) in the context of audio data representations. DML is a technique that leverages deep neural networks to automatically learn hierarchical representations from raw audio waveforms, aiming to capture the intricate...
| Main Author: | |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
Πανεπιστήμιο Πελοποννήσου
2023
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.26263/amitos-1178 https://amitos.library.uop.gr/xmlui/handle/123456789/7675 |
| Summary: | Μ.Δ.Ε. 94 ... : This master thesis explores the application of Deep Metric Learning (DML) in the context of audio data representations. DML is a technique that leverages deep neural networks to automatically learn hierarchical representations from raw audio waveforms, aiming to capture the intricate relationships between audio samples. The central objective of this research is to evaluate the effectiveness of two prominent loss functions, Triplet Loss and Contrastive Loss, and their impact on creating meaningful audio embeddings. These embeddings are crucial for preserving the inherent similarities and dissimilarities between audio samples. In the investigation of Triplet Loss, eight different models were trained using Convolutional Neural Networks (CNNs), with the goal of optimizing the embeddings to position anchor points closer to their respective positive samples while maintaining a significant distance from negative samples. The research considered various distance metrics and scalers to assess their impact on the ... |
|---|