Multi-Task Learning for Improved Recognition of Multiple Types of Acoustic Information
We propose a new method for improving the recognition performance of phonemes, speech emotions, and music genres using multi-task learning. When tasks are closely related, multi-task learning can improve the performance of each task by learning common feature representation for all the tasks. Howeve...
Saved in:
Published in | IEICE Transactions on Information and Systems Vol. E104.D; no. 10; pp. 1762 - 1765 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Tokyo
The Institute of Electronics, Information and Communication Engineers
01.10.2021
Japan Science and Technology Agency |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We propose a new method for improving the recognition performance of phonemes, speech emotions, and music genres using multi-task learning. When tasks are closely related, multi-task learning can improve the performance of each task by learning common feature representation for all the tasks. However, the recognition tasks considered in this study demand different input signals of speech and music at different time scales, resulting in input features with different characteristics. In addition, a training dataset with multiple labels for all information sources is not available. Considering these issues, we conduct multi-task learning in a sequential training process using input features with a single label for one information source. A comparative evaluation confirms that the proposed method for multi-task learning provides higher performance for all recognition tasks than individual learning for each task as in conventional methods. |
---|---|
ISSN: | 0916-8532 1745-1361 |
DOI: | 10.1587/transinf.2021EDL8029 |