Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911998016487424 |
|---|---|
| author | Greif, Jonathan Schmid, Florian Primus, Paul Widmer, Gerhard |
| author_facet | Greif, Jonathan Schmid, Florian Primus, Paul Widmer, Gerhard |
| contents | Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers the more intuitive and convenient approach compared to text-based search. To fully leverage QBV, developing robust audio feature representations for both the vocal imitation and the original sound is crucial. In this paper, we present a new system for QBV that utilizes the feature extraction capabilities of Convolutional Neural Networks pre-trained with large-scale general-purpose audio datasets. We integrate these pre-trained models into a dual encoder architecture and fine-tune them end-to-end using contrastive learning. A distinctive aspect of our proposed method is the fine-tuning strategy of pre-trained models using an adapted NT-Xent loss for contrastive learning, creating a shared embedding space for reference recordings and vocal imitations. The proposed system significantly enhances audio retrieval performance, establishing a new state of the art on both coarse- and fine-grained QBV tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11638 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining Greif, Jonathan Schmid, Florian Primus, Paul Widmer, Gerhard Audio and Speech Processing Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers the more intuitive and convenient approach compared to text-based search. To fully leverage QBV, developing robust audio feature representations for both the vocal imitation and the original sound is crucial. In this paper, we present a new system for QBV that utilizes the feature extraction capabilities of Convolutional Neural Networks pre-trained with large-scale general-purpose audio datasets. We integrate these pre-trained models into a dual encoder architecture and fine-tune them end-to-end using contrastive learning. A distinctive aspect of our proposed method is the fine-tuning strategy of pre-trained models using an adapted NT-Xent loss for contrastive learning, creating a shared embedding space for reference recordings and vocal imitations. The proposed system significantly enhances audio retrieval performance, establishing a new state of the art on both coarse- and fine-grained QBV tasks. |
| title | Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.11638 |