Paper Reading AI Learner

Transformer with Gaussian weighted self-attention for speech enhancement

2019-10-13 23:28:07
Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee

Abstract

The Transformer architecture recently replaced recurrent neural networks such as LSTM or GRU on many natural language processing (NLP) tasks by presenting new state of the art performance. Self-attention is a core building block for Transformer, which not only enables parallelization of sequence computation but also provides the constant path length between symbols that is essential to learn long-range dependencies. However, Transformer did not perform well for speech enhancement due to the lack of consideration for speech and noise physical characteristics. In this paper, we propose Gaussian weighted self-attention that attenuates attention weights according to the distance between target and context symbols. The experimental results showed that the proposed attention scheme significantly improved over the original Transformer as well as recurrent networks.

Abstract (translated)

URL

https://arxiv.org/abs/1910.06762

PDF

https://arxiv.org/pdf/1910.06762.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot