All Issue

2016 Vol.35, Issue 4 Preview Page
Audio signal clustering and separation using a stacked autoencoder

복층 자기부호화기를 이용한 음향 신호 군집화 및 분리

Gil-Jin Jang1*
장 길진1*
1School of Electronics Engineering, Kyungpook National University
1경북대학교 전자공학부
*교신저자. *Corresponding Author. 
31 July 2016. pp. 303-309
PDF XML Citation
Abstract

This paper proposes a novel approach to the problem of audio signal clustering using a stacked autoencoder. The proposed stacked autoencoder learns an efficient representation for the input signal, enables clustering constituent signals with similar characteristics, and therefore the original sources can be separated based on the clustering results. STFT (Short-Time Fourier Transform) is performed to extract time-frequency spectrum, and rectangular windows at all the possible locations are used as input values to the autoencoder. The outputs at the middle, encoding layer, are used to cluster the rectangular windows and the original sources are separated by the Wiener filters derived from the clustering results. Source separation experiments were carried out in comparison to the conventional NMF (Non-negative Matrix Factorization), and the estimated sources by the proposed method well represent the characteristics of the orignal sources as shown in the time-frequency representation.

Keywords
Audio signal separation
Autoencoder
Deep neural networks
Audio clustering

본 논문은 자기부호화기를 이용한 음향신호 분리방법을 제안한다. 사용된 복층구조 신경망 자기부호화기는 입력 신호의 효율적인 표현방법을 자동으로 학습하며, 유사한 특징을 가지고 있는 요소신호들을 군집함으로써 다른 특징의 신호들을 분리할 수 있다. 시간영역과 주파수영역의 변이특성을 추출하기 위하여 단구간푸리에변환(Short- Time Fourier Transform, STFT)을 수행하였으며, 정해진 크기의 사각형 창을 모든 가능한 위치에 적용하여 얻은 단구간 주파수 스펙트럼을 자기부호화기의 입력으로 사용하였다. 자기부호화기의 부호노드들의 값을 이용하여 유사한 스펙트럼 창들을 군집하고, 이를 이용하여 원래의 음원들로 분리해 낼 수 있었다. 분리된 원음들은 원래의 입력신호의 특징을 확실히 나타내었으며, 기존의 비음수 행렬분해(Non-negative Matrix Factorization, NMF) 결과와 주파수 스펙트럼 비교를 통해 그 유효성을 보일 수 있었다.

키워드
음향신호 분리
자기부호화기
심화신경회로망
음향신호 군집
References
1
1.G. Hu and D. Wang, “Monaural speech segregation based on pitch tracking and amplitude   modulation,” IEEE Trans. on Neural Networks 15, 1135-1150 (2004).
2
2.B. Raj, T. Virtanen, S. Chaudhuri, and R. Singh, “Non-negative matrix factorization based compensation of music for automatic speech recognition,” Proc. Interspeech, 717-720 (2010).
3
3.P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol, “Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion,” JMLR 11, 3371-3408 (2010).
4
4.G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science 313, 504-507 (2006).
5
5.G. E. Hinton, S. Osindero, and Y. Teh, “A fast learning algorithm for deep belief nets,” Neural Computation 18, 1527-1554 (2006).
Information
  • Publisher :The Acoustical Society of Korea
  • Publisher(Ko) :한국음향학회
  • Journal Title :The Journal of the Acoustical Society of Korea
  • Journal Title(Ko) :한국음향학회지
  • Volume : 35
  • No :4
  • Pages :303-309
  • Received Date : 2016-06-09
  • Revised Date : 2016-06-22
  • Accepted Date : 2016-06-13
  • DOI :https://doi.org/10.7776/ASK.2016.35.4.303
Journal Informaiton The Journal of the Acoustical Society of Korea The Journal of the Acoustical Society of Korea
E-Book
  • scopus_JASK
  • ESCI_JASK
  • Google scholar_JASK
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • ccl
Journal Informaiton Journal Informaiton - close