ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술지 Ensemble-Guided Model for Performance Enhancement in Model-Complexity-Limited Acoustic Scene Classification
Cited 3 time in scopus Download 73 time Share share facebook twitter linkedin kakaostory
이석진, 김민한, 신승현, 백승재, 박수영, 정영호
Applied Sciences, v.12 no.1, pp.1-15
21HS3900, 신체기능의 이상이나 저하를 극복하기 위한 휴먼 청각 및 근력 증강 원천 기술 개발, 신형철
In recent acoustic scene classification (ASC) models, various auxiliary methods to enhance performance have been applied, e.g., subsystem ensembles and data augmentations. Particularly, the ensembles of several submodels may be effective in the ASC models, but there is a problem with increasing the size of the model because it contains several submodels. Therefore, it is hard to be used in model-complexity-limited ASC tasks. In this paper, we would like to find the performance enhancement method while taking advantage of the model ensemble technique without increasing the model size. Our method is proposed based on a mean-teacher model, which is developed for consistency learning in semi-supervised learning. Because our problem is supervised learning, which is different from the purpose of the conventional mean-teacher model, we modify detailed strategies to maximize the consistency learning performance. To evaluate the effectiveness of our method, experiments were performed with an ASC database from the Detection and Classification of Acoustic Scenes and Events 2021 Task 1A. The small-sized ASC model with our proposed method improved the log loss performance up to 1.009 and the F1-score performance by 67.12%, whereas the vanilla ASC model showed a log loss of 1.052 and an F1-score of 65.79%.
KSP 제안 키워드
Acoustic Scene Classification, Enhance performance, Enhancement method, F1-score, Learning performance, Loss performance, Model ensemble, Semi-Supervised Learning(SSL), Small-sized, Teacher Model, detection and classification
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)