Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
원문 초록
Predicting the altered acoustic frames is an effective way of self-supervised learning for speech representation. However, it is challenging to prevent the pretrained model from overfitting. In this paper, we proposed to introduce two dropout regularization methods into the pretraining of transformer encoder: (1) attention dropout, (2) layer dropout. Both of the two dropout methods encourage the model to utilize global speech information, and avoid just copying local spectrum features when reconstructing the masked frames. We evaluated the proposed methods on phoneme classification and speaker recognition tasks. The experiments demonstrate that our dropout approaches achieve competitive results, and improve the performance of classification accuracy on downstream tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Synthetic Speech Source Tracing using Metric Learning
Detecting Side Effects of Adverse Drug Reactions Through Drug-Drug Interactions Using Graph Neural Networks and Self-Supervised Learning
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Hybrid-View Attention for csPCa Classification in TRUS
RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.