The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Propomos um novo método para melhorar o desempenho de reconhecimento de fonemas, emoções de fala e gêneros musicais usando aprendizagem multitarefa. Quando as tarefas estão intimamente relacionadas, o aprendizado multitarefa pode melhorar o desempenho de cada tarefa, aprendendo a representação de recursos comuns para todas as tarefas. Contudo, as tarefas de reconhecimento consideradas neste estudo exigem diferentes sinais de entrada de fala e música em diferentes escalas de tempo, resultando em recursos de entrada com características diferentes. Além disso, não está disponível um conjunto de dados de treinamento com vários rótulos para todas as fontes de informação. Considerando essas questões, conduzimos o aprendizado multitarefa em um processo de treinamento sequencial usando recursos de entrada com um único rótulo para uma fonte de informação. Uma avaliação comparativa confirma que o método proposto para a aprendizagem multitarefa proporciona maior desempenho para todas as tarefas de reconhecimento do que a aprendizagem individual para cada tarefa, como nos métodos convencionais.
Jae-Won KIM
Kwangwoon University
Hochong PARK
Kwangwoon University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Jae-Won KIM, Hochong PARK, "Multi-Task Learning for Improved Recognition of Multiple Types of Acoustic Information" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 10, pp. 1762-1765, October 2021, doi: 10.1587/transinf.2021EDL8029.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8029/_p
Copiar
@ARTICLE{e104-d_10_1762,
author={Jae-Won KIM, Hochong PARK, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Task Learning for Improved Recognition of Multiple Types of Acoustic Information},
year={2021},
volume={E104-D},
number={10},
pages={1762-1765},
abstract={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.},
keywords={},
doi={10.1587/transinf.2021EDL8029},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - Multi-Task Learning for Improved Recognition of Multiple Types of Acoustic Information
T2 - IEICE TRANSACTIONS on Information
SP - 1762
EP - 1765
AU - Jae-Won KIM
AU - Hochong PARK
PY - 2021
DO - 10.1587/transinf.2021EDL8029
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2021
AB - 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.
ER -