Abstract
A new speech enhancement architecture using convolutive blind signal separation (CBSS) and subspace-based speech enhancement is presented. The spatial and spectral information are integrated to enhance the target speech signal and suppress both interference noise and background noise. Real-world experiments were carried out in a noisy office room. Experimental results demonstrate the superiority of the proposed architecture.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
VanVeen BD, Buckley KM (1988) Beamforming: a versatile approach to spatial filtering. IEEE Acoust, Speech Sig Process Mag 5:4–24
Kellermann W (1991) A self-steering digital microphone array. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing, vol 5, April pp 3581–3584
Low SY, Nordholm S, Togneri R (2004) Convolutive blind signal separation with post-processing. IEEE Trans Speech Audio Process 12(5):539–548
Visser E, Otsuka M, Lee TW (2003) A spatio-temporal speech enhancement scheme for robust speech recognition in noisy environments. Speech Commun 41(2):393–407
Parra L, Spence C (2000) Convolutive blind source separation of nonstationary sources. IEEE Trans Speech Audio Process 8(3):320–327
Parra L, Fancourt C (2002) An adaptive beamforming perspective on convolutive blind source separation. Davis G (ed) In: noise reduction in speech applications, CRC Press LLC
Ephraim Y, Van Trees HL (1995) A signal subspace approach for speech enhancement. IEEE Trans Speech Audio Process 3(4):251–266
Zwicker E, Terhardt E (1980) Analytical expressions for critical-band rate and critical bandwidth as a function of frequency. J Acoust Soc Am 68:1523–1525
Chen SH, Wang JF (2004) Speech enhancement using perceptual wavelet packet decomposition and Teager energy operator. J VLSI Sig Process Syst 36(2–3):125–139
Yang W, Benbouchta M, Yantorno R (1998) Performance of the modified bark spectral distortion as an objective speech quality measure. In: Proceedings of IEEE international conference on acoust, speech, signal process pp 541–544
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media Dordrecht
About this paper
Cite this paper
Lin, CH. et al. (2014). Blind Signal Separation with Speech Enhancement. In: Huang, YM., Chao, HC., Deng, DJ., Park, J. (eds) Advanced Technologies, Embedded and Multimedia for Human-centric Computing. Lecture Notes in Electrical Engineering, vol 260. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-7262-5_119
Download citation
DOI: https://doi.org/10.1007/978-94-007-7262-5_119
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-7261-8
Online ISBN: 978-94-007-7262-5
eBook Packages: EngineeringEngineering (R0)