The Library
Self-supervised graphs for audio representation learning with limited labeled data
Tools
Tools
Tools
Shirian, Amir, Somandepalli, Krishna and Guha, Tanaya (2022) Self-supervised graphs for audio representation learning with limited labeled data. IEEE Journal of Selected Topics in Signal Processing, 16 (6). pp. 1391-1401. doi:10.1109/JSTSP.2022.3190083 ISSN 1932-4553.
|
PDF
WRAP-self-supervised-graphs-audio-representation-learning-limited-labeled-data-2022.pdf - Accepted Version - Requires a PDF viewer. Download (4Mb) | Preview |
Official URL: http://dx.doi.org/10.1109/JSTSP.2022.3190083
Abstract
Large-scale databases with high-quality manual labels are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a graph node, we propose a subgraph-based framework with novel selfsupervision tasks to learn effective audio representations. During training, subgraphs are constructed by sampling the entire pool of available training data to exploit the relationship between the labelled and unlabeled audio samples. During inference, we use random edges to alleviate the overhead of graph construction. We evaluate our model on three benchmark audio datasets spanning two tasks: acoustic event classification and speech emotion recognition. We show that our semi-supervised model performs better or on par with fully supervised models and outperforms several competitive existing models. Our model is compact and can produce generalized audio representations robust to different types of signal noise. Our code is available at github.com/AmirSh15/SSL_graph_audio.
| Item Type: | Journal Article | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||||
| Library of Congress Subject Headings (LCSH): | Neural networks (Computer science), Graph theory -- Data processing, Speech processing systems, Deep learning (Machine learning), Emotions -- Data processing, Automatic speech recognition | ||||||||
| Journal or Publication Title: | IEEE Journal of Selected Topics in Signal Processing | ||||||||
| Publisher: | IEEE | ||||||||
| ISSN: | 1932-4553 | ||||||||
| Official Date: | October 2022 | ||||||||
| Dates: |
|
||||||||
| Volume: | 16 | ||||||||
| Number: | 6 | ||||||||
| Page Range: | pp. 1391-1401 | ||||||||
| DOI: | 10.1109/JSTSP.2022.3190083 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Reuse Statement (publisher, data, author rights): | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | ||||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||||
| Date of first compliant deposit: | 19 July 2022 | ||||||||
| Date of first compliant Open Access: | 20 July 2022 |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
