Title:
ABNORMAL SOUND DETECTION LEARNING DEVICE, ACOUSTIC FEATURE VALUE EXTRACTION DEVICE, ABNORMAL SOUND SAMPLING DEVICE, AND METHOD AND PROGRAM FOR SAME
Document Type and Number:
WIPO Patent Application WO/2017/171051
Kind Code:
A1
Abstract:
The abnormal sound detection learning device according to the present invention includes a first acoustic feature value extraction unit for extracting an acoustic feature value of a normal sound on the basis of normal sound learning data using an acoustic feature value extraction function, a normal sound model updating unit for updating a normal sound model using the extracted acoustic feature value, a second acoustic feature value extraction unit for extracting an acoustic feature value of an abnormal sound on the basis of a simulated abnormal sound and extracting an acoustic feature value of a normal sound on the basis of normal sound learning data using the acoustic feature value extraction function, and an acoustic feature value extraction function updating unit for updating the acoustic feature value extraction function using the extracted abnormal sound acoustic feature value and normal sound acoustic feature value, and the abnormal sound detection learning device repeats the processing of the units described above.
Inventors:
KOIZUMI YUMA (JP)
SAITO SHOICHIRO (JP)
UEMATSU HISASHI (JP)
NIWA KENTA (JP)
ITO HIROAKI (JP)
SAITO SHOICHIRO (JP)
UEMATSU HISASHI (JP)
NIWA KENTA (JP)
ITO HIROAKI (JP)
Application Number:
PCT/JP2017/013738
Publication Date:
October 05, 2017
Filing Date:
March 31, 2017
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G01H17/00; G01M99/00; G01N29/12; G01N29/44; G06N99/00; G10L15/10; G10L25/48
Domestic Patent References:
| WO2015011791A1 | 2015-01-29 |
Foreign References:
| JP2012181280A | 2012-09-20 | |||
| JPH08271573A | 1996-10-18 | |||
| JPH0219960A | 1990-01-23 | |||
| JPH04106429A | 1992-04-08 | |||
| JP2008145988A | 2008-06-26 |
Other References:
SAINATH T.N. ET AL.: "Learning Filter Banks within a Deep Neural Network Framework", IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 8 December 2013 (2013-12-08), pages 297 - 302, XP032544226
PFISTER LUKE ET AL.: "Learning Sparsifying Filter Banks", SPIE PROCEEDINGS, vol. 9597, 24 August 2015 (2015-08-24), XP060060332
BIEM ALAIN ET AL.: "An Application of Discriminative Feature Extraction to Filter-Bank-Based Speech Recognition", IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, vol. 9, no. 2, February 2001 (2001-02-01), pages 96 - 110, XP011054071
See also references of EP 3438623A4
PFISTER LUKE ET AL.: "Learning Sparsifying Filter Banks", SPIE PROCEEDINGS, vol. 9597, 24 August 2015 (2015-08-24), XP060060332
BIEM ALAIN ET AL.: "An Application of Discriminative Feature Extraction to Filter-Bank-Based Speech Recognition", IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, vol. 9, no. 2, February 2001 (2001-02-01), pages 96 - 110, XP011054071
See also references of EP 3438623A4
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF:
Previous Patent: WELDED STRUCTURAL MEMBER
Next Patent: CARRIER AND SUBSTRATE MANUFACTURING METHOD USING THIS CARRIER
Next Patent: CARRIER AND SUBSTRATE MANUFACTURING METHOD USING THIS CARRIER