Speech Enhancement Using Joint DNN-NMF Model Learned with Multi-Objective Frequency Differential Spectrum Loss Function
We propose a multi-objective joint model of non-negative matrix factorization (NMF) and deep neural network (DNN) with a new loss function for speech enhancement. The proposed loss function (LMOFD) is a weighted combination of a frequency differential spectrum mean squared error (MSE)-based loss fun...
Saved in:
Main Authors: | Matin Pashaian, Sanaz Seyedin |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-01-01
|
Series: | IET Signal Processing |
Online Access: | http://dx.doi.org/10.1049/2024/8881007 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition
by: Sanaz Seyedin, et al.
Published: (2013-01-01) -
Time-Frequency Feature Extraction of HRRP Using AGR and NMF for SAR ATR
by: Xinzheng Zhang, et al.
Published: (2015-01-01) -
Extraction of Fetal Electrocardiogram by Combining Deep Learning and SVD-ICA-NMF Methods
by: Said Ziani, et al.
Published: (2023-09-01) -
Effects of Various Extents of High-Frequency Hearing Loss on Speech Recognition and Gap Detection at Low Frequencies in Patients with Sensorineural Hearing Loss
by: Bei Li, et al.
Published: (2017-01-01) -
Mobile Performance Intelligent Evaluation of IoT Networks Based on DNN
by: Zhen Tang, et al.
Published: (2022-01-01)