Joint Optimization of Deep Neural Network-Based Dereverberation and Beamforming for Sound Event Detection in Multi-Channel Environments
In this paper, we propose joint optimization of deep neural network (DNN)-supported dereverberation and beamforming for the convolutional recurrent neural network (CRNN)-based sound event detection (SED) in multi-channel environments. First, the short-time Fourier transform (STFT) coefficients are c...
Main Authors: | Kyoungjin Noh, Joon-Hyuk Chang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/7/1883 |
Similar Items
-
Subspace Methods for Multimicrophone Speech Dereverberation
by: Moonen Marc, et al.
Published: (2003-01-01) -
Late Reverberant Spectral Variance Estimation for Single-Channel Dereverberation Using Adaptive Parameter Estimator
by: Zhaoqi Zhang, et al.
Published: (2021-08-01) -
An online algorithm for echo cancellation, dereverberation and noise reduction based on a Kalman-EM Method
by: Nili Cohen, et al.
Published: (2021-08-01) -
Single-Microphone Speech Dereverberation: Modulation Domain Processing and Quality Assessment
by: ZHENG, CHENXI
Published: (2011) -
A reverberation-time-aware DNN approach leveraging spatial information for microphone array dereverberation
by: Bo Wu, et al.
Published: (2017-12-01)