Title:
SIGNAL PROCESSING DEVICE USING NEURAL NETWORK, SIGNAL PROCESSING METHOD USING NEURAL NETWORK, AND SIGNAL PROCESSING PROGRAM
Document Type and Number:
WIPO Patent Application WO/2019/026973
Kind Code:
A1
Abstract:
This signal processing device (10), which estimates a signal in which a reverberation is reduced from an observation signal that contains the reverberation observed from one or more microphones, includes: a power estimation unit (12) which estimates an estimation value of a feature amount corresponding to the power of the signal, in which the reverberation corresponding to the observation signal is reduced, by inputting an observation feature amount corresponding to the observation signal to a neural network that receives a feature amount of a reverberation-containing signal and is learnt to output an estimation value of the feature amount corresponding to the power of the signal in which the reverberation in the signal is reduced; and a regression coefficient estimation unit (13) which estimates regression coefficients in an autoregressive process that generates the observation signal, by using the estimation value of the feature amount corresponding to power that is an estimation effect of the power estimation unit (12).
Inventors:
KINOSHITA KEISUKE (JP)
NAKATANI TOMOHIRO (JP)
DELCROIX MARC (JP)
NAKATANI TOMOHIRO (JP)
DELCROIX MARC (JP)
Application Number:
PCT/JP2018/028910
Publication Date:
February 07, 2019
Filing Date:
August 01, 2018
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L21/0264
Other References:
KINOSHITA, K. ET AL.: "Neural network-based spectrum estimation for online WPE dereverberation", PROC. INTERSPEECH 2017, 20 August 2017 (2017-08-20) - 24 August 2017 (2017-08-24), pages 384 - 388, XP055572238
NAKATANI, T. ET AL.: "Speech dereverberation based on variance-normalized delayed linear prediction , IEEE Trans. on Audio", SPEECH, AND LANGUAGE PROCESSING, vol. 18, no. 7, September 2010 (2010-09-01), pages 1717 - 1731, XP011316583
ISHII, T. ET AL.: "Reverberant speech recognition based on denoising autoencoder", PROC. INTERSPEECH 2013, ISCA, 25 August 2013 (2013-08-25) - 29 August 2013 (2013-08-29), pages 3512 - 3516, XP055572244
NAKATANI, T. ET AL.: "Speech dereverberation based on variance-normalized delayed linear prediction , IEEE Trans. on Audio", SPEECH, AND LANGUAGE PROCESSING, vol. 18, no. 7, September 2010 (2010-09-01), pages 1717 - 1731, XP011316583
ISHII, T. ET AL.: "Reverberant speech recognition based on denoising autoencoder", PROC. INTERSPEECH 2013, ISCA, 25 August 2013 (2013-08-25) - 29 August 2013 (2013-08-29), pages 3512 - 3516, XP055572244
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: