Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network for Speech Enhancement

2021-04-12 · Liming Zhou, Yongyu Gao, Ziluo Wang, Jiwei Li, Wenbin Zhang

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum,via a naive convolution neural network or recurrent neural network.Some recent studies were based on Complex spectral Mapping convolution recurrent neural network (CRN) . These models skiped directly from encoder layers' output and decoder layers' input ,which maybe thoughtless. We proposed an attention mechanism based skip connection between encoder and decoder layers,namely Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network (CARN).Compared with CRN model,the proposed CARN model improved more than 10% relatively at several metrics such as PESQ,CBAK,COVL,CSIG and son,and outperformed the place 1st model in both real time and non-real time track of the DNS Challenge 2020 at these metrics.

📄 PDF Abstract BibTeX arXiv:2104.05267

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Speech Enhancement

Methods 이 논문이 사용한 방법론

CRN Conditional Relation Network, or CRN, is a building block to construct more sophisticated structures for representation and reasoning over video. CRN takes as input an…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation

2022-11-22 · Vinay Kothapally, John H. L. Hansen

Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studie…

Automatic Speech Recognition Automatic Speech Recognition (ASR)Speech Dereverberation speech-recognition+1

AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling

2024-06-17 · Vahid Ahmadi Kalkhorani, Cheng Yu, Anurag Kumar, Ke Tan 외

Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an \gls{av} system for speech enhancement, target speaker extraction, and multi-talker speaker se…

Speaker Separation Speech Enhancement Speech Separation Target Speaker Extraction

CLAReSNet: When Convolution Meets Latent Attention for Hyperspectral Image Classification

2025-11-15 · Asmit Bandyopadhyay, Anindita Das Bhattacharjee, Rakesh Das arxiv

Hyperspectral image (HSI) classification faces critical challenges, including high spectral dimensionality, complex spectral-spatial correlations, and limited training samples with severe class imbalance. While CNNs exce…

Hyperspectral Image Classification

A Convolutional Neural Network with Mapping Layers for Hyperspectral Image Classification

2019-08-26 · Rui Li, Zhibin Pan, Yang Wang, Ping Wang

In this paper, we propose a convolutional neural network with mapping layers (MCNN) for hyperspectral image (HSI) classification. The proposed mapping layers map the input patch into a low dimensional subspace by multili…

Classification General Classification Hyperspectral Image Classification image-classification+1

PaperNet: Efficient Temporal Convolutions and Channel Residual Attention for EEG Epilepsy Detection

2025-12-17 · Md Shahriar Sajid, Abhijit Kumar Ghosh, Fariha Nusrat arxiv

Electroencephalography (EEG) signals contain rich temporal-spectral structure but are difficult to model due to noise, subject variability, and multi-scale dynamics. Lightweight deep learning models have shown promise, y…