https://scholars.lib.ntu.edu.tw/handle/123456789/581362
標題: | SERIL: Noise adaptive speech enhancement using regularization-based incremental learning | 作者: | Lee C.-C Lin Y.-C Wang H.-M Tsao Y. HSUAN-TIEN LIN |
關鍵字: | Digital storage; Speech communication; Speech enhancement; Adaptive technique; Catastrophic forgetting; Embedded device; Incremental learning; Learning models; Noise adaptation; Noise environments; Training data; Deep learning | 公開日期: | 2020 | 卷: | 2020-October | 起(迄)頁: | 2432-2436 | 來源出版物: | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 摘要: | Numerous noise adaptation techniques have been proposed to fine-tune deep-learning models in speech enhancement (SE) for mismatched noise environments. Nevertheless, adaptation to a new environment may lead to catastrophic forgetting of the previously learned environments. The catastrophic forgetting issue degrades the performance of SE in real-world embedded devices, which often revisit previous noise environments. The nature of embedded devices does not allow solving the issue with additional storage of all pre-trained models or earlier training data. In this paper, we propose a regularization-based incremental learning SE (SERIL) strategy, complementing existing noise adaptation strategies without using additional storage. With a regularization constraint, the parameters are updated to the new noise environment while retaining the knowledge of the previous noise environments. The experimental results show that, when faced with a new noise domain, the SERIL model outperforms the unadapted SE model. Meanwhile, compared with the current adaptive technique based on fine-tuning, the SERIL model can reduce the forgetting of previous noise environments by 52%. The results verify that the SERIL model can effectively adjust itself to new noise environments while overcoming the catastrophic forgetting issue. The results make SERIL a favorable choice for real-world SE applications, where the noise environment changes frequently. ? 2020 ISCA |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85095556352&doi=10.21437%2fInterspeech.2020-2213&partnerID=40&md5=45a4e166b8f2964998ec61cbf465bae1 https://scholars.lib.ntu.edu.tw/handle/123456789/581362 |
ISSN: | 2308457X | DOI: | 10.21437/Interspeech.2020-2213 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。