Inicio  /  Information  /  Vol: 14 Par: 7 (2023)  /  Artículo
ARTÍCULO
TITULO

Ensemble System of Deep Neural Networks for Single-Channel Audio Separation

Musab T. S. Al-Kaltakchi    
Ahmad Saeed Mohammad and Wai Lok Woo    

Resumen

Speech separation is a well-known problem, especially when there is only one sound mixture available. Estimating the Ideal Binary Mask (IBM) is one solution to this problem. Recent research has focused on the supervised classification approach. The challenge of extracting features from the sources is critical for this method. Speech separation has been accomplished by using a variety of feature extraction models. The majority of them, however, are concentrated on a single feature. The complementary nature of various features have not been thoroughly investigated. In this paper, we propose a deep neural network (DNN) ensemble architecture to completely explore the complimentary nature of the diverse features obtained from raw acoustic features. We examined the penultimate discriminative representations instead of employing the features acquired from the output layer. The learned representations were also fused to produce a new features vector, which was then classified by using the Extreme Learning Machine (ELM). In addition, a genetic algorithm (GA) was created to optimize the parameters globally. The results of the experiments showed that our proposed system completely considered various features and produced a high-quality IBM under different conditions.

 Artículos similares

       
 
Jun Jian, Jinhai Chen and Peter J. Webster    
Ship pilots and maritime safety administration have an urgent need for more accurate and earlier warnings for strong wind gusts. This study firstly investigated the ?Oriental Star? cruise ship capsizing event in 2015, one of the deadliest shipwreck event... ver más

 
Franco Bagnoli and Michele Baia    
We explore several aspects of replica synchronization with the goal of retrieving the values of parameters applied to the Lorenz system. The idea is to establish a computer replica (slave) of a natural system (master, simulated in this paper), and exploi... ver más
Revista: Algorithms

 
Anfal Ahmed Aleidan, Qaisar Abbas, Yassine Daadaa, Imran Qureshi, Ganeshkumar Perumal, Mostafa E. A. Ibrahim and Alaa E. S. Ahmed    
User authentication has become necessary in different life domains. Traditional authentication methods like personal information numbers (PINs), password ID cards, and tokens are vulnerable to attacks. For secure authentication, methods like biometrics h... ver más
Revista: Applied Sciences

 
Keyvan Salehi Paniagua, Pablo García-Fogeda and Félix Arévalo    
In this work, the aeroelastic stability of an aerial refueling system is investigated. The system is formed by a classical hose and drogue, and the novelty of our work is the inclusion of a grid fin configuration to improve its stability. The unsteady ae... ver más
Revista: Aerospace

 
Abhilash Pati, Manoranjan Parhi, Mohammad Alnabhan, Binod Kumar Pattanayak, Ahmad Khader Habboush and Mohammad K. Al Nawayseh    
Recently, it has proven difficult to make an immediate remote diagnosis of any coronary illness, including heart disease, diabetes, etc. The drawbacks of cloud computing infrastructures, such as excessive latency, bandwidth, energy consumption, security,... ver más
Revista: Informatics