ITM Web Conf.
Volume 47, 20222022 2nd International Conference on Computer, Communication, Control, Automation and Robotics (CCCAR2022)
|Number of page(s)||7|
|Section||Algorithm Optimization and Application|
|Published online||23 June 2022|
Improved features using convolution-augmented transformers for keyword spotting
1 Unit 91977 of PLA, Beijing, China
2 College of Electronic Countermeasures, National University of Defence Technology, Hefei, China
* Corresponding author: email@example.com
Transformer can effectively model long rang dependency, but suffer from uncapable to extract local feature patterns. While CNNs exploit local features effectively. In this paper, we seek to combine convolution and Transformers improves over using them individually, and propose improved features using convolution-augmented transformers for keyword spotting. The convolution-augmented transformers are constructed with a ResNet front-end and a convolution-augmented transformers back-end in series. Using this improved feature for keyword spotting task. The results show that the improved features using convolution- augmented transformers can yield at least 3% improvement compared with other features.
Key words: Keyword spotting / Attention / Convolutional neural networks / Transformers
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.