Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SIGNAL PROCESSING DEVICE, LEARNING DEVICE, SIGNAL PROCESSING METHOD, LEARNING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/170907
Kind Code:
A1
Abstract:
The signal processing device according to an embodiment of the present invention comprises: a conversion unit that converts an inputted mixed acoustic signal into a plurality of first internal states; a weighting unit that, when auxiliary information relating to an acoustic signal of a target sound source is inputted, generates a second internal state being the weighted sum of the plurality of first internal states on the basis of the auxiliary information, and when the auxiliary information is not inputted, generates the second internal state by selecting any of the plurality of first internal states; and a mask estimation unit that estimates a mask on the basis of the second internal state.

Inventors:
OCHIAI TSUBASA (JP)
DELCROIX MARC (JP)
KINOSHITA KEISUKE (JP)
OGAWA ATSUNORI (JP)
NAKATANI TOMOHIRO (JP)
Application Number:
PCT/JP2020/005332
Publication Date:
August 27, 2020
Filing Date:
February 12, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L21/0272; G10L25/30
Domestic Patent References:
WO2019017403A12019-01-24
Foreign References:
Other References:
MARC DELCROIX, KATERINA ZMOLIKOVA: "SpeakerBeam", NTT, vol. 30, no. 9, September 2018 (2018-09-01), pages 12 - 15, XP055735037, Retrieved from the Internet
CHEN, XIUYI ET AL.: "Distilled Binary Neural Network for Monaural Speech Separation", 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), July 2018 (2018-07-01), pages 1 - 8, XP033419263, Retrieved from the Internet DOI: 10.1109/IJCNN.2018.8489456
Attorney, Agent or Firm:
ITOH, Tadashige et al. (JP)
Download PDF: