Paper Reading AI Learner

Deep Network Perceptual Losses for Speech Denoising

2020-11-21 02:36:58
Mark R. Saddler, Andrew Francl, Jenelle Feather, Kaizhi Qian, Yang Zhang, Josh H. McDermott

Abstract

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. Here we investigate whether deep feature representations learned for audio classification tasks can be used to improve denoising. We first trained deep neural networks to classify either spoken words or environmental sounds from audio. We then trained an audio transform to map noisy speech to an audio waveform that minimized 'perceptual' losses derived from the recognition network. When the transform was trained to minimize the difference in the deep feature representations between the output audio and the corresponding clean audio, it removed noise substantially better than baseline methods trained to reconstruct clean waveforms. The learned deep features were essential for this improvement, as features from untrained networks with random weights did not provide the same benefit. The results suggest the use of deep features as perceptual metrics to guide speech enhancement.

Abstract (translated)

URL

https://arxiv.org/abs/2011.10706

PDF

https://arxiv.org/pdf/2011.10706.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