Blind source separation by multilayer neural network classifiers for spectrogram analysis

This paper describes a novel method for blind source separation using multilayer neural networks when an audio signal has been recorded in a room with reverberation or with moving signal sources. In conventional applications, speech-recognition specialists can identify the signal from a specific spe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Toshihiko SHIRAISHI, Tomoki DOURA
Formato:	article
Lenguaje:	EN
Publicado:	The Japan Society of Mechanical Engineers 2019
Materias:	blind source separation multilayer neural network classifier spectrogram analysis convolutive mixture time-varying system Mechanical engineering and machinery TJ1-1570
Acceso en línea:	https://doaj.org/article/7de2a8f33f734966bd0437d08dd14fa8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7de2a8f33f734966bd0437d08dd14fa8
record_format	dspace
spelling	oai:doaj.org-article:7de2a8f33f734966bd0437d08dd14fa82021-11-29T05:48:33ZBlind source separation by multilayer neural network classifiers for spectrogram analysis2187-974510.1299/mej.18-00527https://doaj.org/article/7de2a8f33f734966bd0437d08dd14fa82019-11-01T00:00:00Zhttps://www.jstage.jst.go.jp/article/mej/6/6/6_18-00527/_pdf/-char/enhttps://doaj.org/toc/2187-9745This paper describes a novel method for blind source separation using multilayer neural networks when an audio signal has been recorded in a room with reverberation or with moving signal sources. In conventional applications, speech-recognition specialists can identify the signal from a specific speaker in a recording of many speakers by analyzing a spectrogram of the recording. The spectrogram is a visual representation of the time series of frequency spectra of a target signal. To use multilayer neural networks for a similar classification task, the proposed method begins by preparing a spectrogram of a mixed signal using the short-time Fourier transform, which is then regarded as a visual object. The spectrogram is then divided into small time-frequency segments and each segment is classified into a class of the corresponding signal source by the multilayer neural networks. After that, an inverse short-time Fourier transform is employed to extract the separated signals. The paper also evaluates the separation performance of this classification algorithm. With the transformation of the blind source separation problem into a classification problem, multilayer neural network classifiers can be used, and they do not require information about the mixing environment, or statistical characteristics of the target signals, or multiple microphones. Simulated tests indicate that the proposed method achieves good separation performance under conditions with reverberation or moving signal sources. The proposed method may be adapted for separating signals from unknown convolutive mixtures and time-varying systems.Toshihiko SHIRAISHITomoki DOURAThe Japan Society of Mechanical Engineersarticleblind source separationmultilayer neural networkclassifierspectrogram analysisconvolutive mixturetime-varying systemMechanical engineering and machineryTJ1-1570ENMechanical Engineering Journal, Vol 6, Iss 6, Pp 18-00527-18-00527 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	blind source separation multilayer neural network classifier spectrogram analysis convolutive mixture time-varying system Mechanical engineering and machinery TJ1-1570
spellingShingle	blind source separation multilayer neural network classifier spectrogram analysis convolutive mixture time-varying system Mechanical engineering and machinery TJ1-1570 Toshihiko SHIRAISHI Tomoki DOURA Blind source separation by multilayer neural network classifiers for spectrogram analysis
description	This paper describes a novel method for blind source separation using multilayer neural networks when an audio signal has been recorded in a room with reverberation or with moving signal sources. In conventional applications, speech-recognition specialists can identify the signal from a specific speaker in a recording of many speakers by analyzing a spectrogram of the recording. The spectrogram is a visual representation of the time series of frequency spectra of a target signal. To use multilayer neural networks for a similar classification task, the proposed method begins by preparing a spectrogram of a mixed signal using the short-time Fourier transform, which is then regarded as a visual object. The spectrogram is then divided into small time-frequency segments and each segment is classified into a class of the corresponding signal source by the multilayer neural networks. After that, an inverse short-time Fourier transform is employed to extract the separated signals. The paper also evaluates the separation performance of this classification algorithm. With the transformation of the blind source separation problem into a classification problem, multilayer neural network classifiers can be used, and they do not require information about the mixing environment, or statistical characteristics of the target signals, or multiple microphones. Simulated tests indicate that the proposed method achieves good separation performance under conditions with reverberation or moving signal sources. The proposed method may be adapted for separating signals from unknown convolutive mixtures and time-varying systems.
format	article
author	Toshihiko SHIRAISHI Tomoki DOURA
author_facet	Toshihiko SHIRAISHI Tomoki DOURA
author_sort	Toshihiko SHIRAISHI
title	Blind source separation by multilayer neural network classifiers for spectrogram analysis
title_short	Blind source separation by multilayer neural network classifiers for spectrogram analysis
title_full	Blind source separation by multilayer neural network classifiers for spectrogram analysis
title_fullStr	Blind source separation by multilayer neural network classifiers for spectrogram analysis
title_full_unstemmed	Blind source separation by multilayer neural network classifiers for spectrogram analysis
title_sort	blind source separation by multilayer neural network classifiers for spectrogram analysis
publisher	The Japan Society of Mechanical Engineers
publishDate	2019
url	https://doaj.org/article/7de2a8f33f734966bd0437d08dd14fa8
work_keys_str_mv	AT toshihikoshiraishi blindsourceseparationbymultilayerneuralnetworkclassifiersforspectrogramanalysis AT tomokidoura blindsourceseparationbymultilayerneuralnetworkclassifiersforspectrogramanalysis
_version_	1718407595545329664

Blind source separation by multilayer neural network classifiers for spectrogram analysis

Ejemplares similares