Title:
PATCHED MULTI-CONDITION TRAINING FOR ROBUST SPEECH RECOGNITION
Document Type and Number:
WIPO Patent Application WO/2023/177095
Kind Code:
A1
Abstract:
A method of obtaining a patched signal for training a model for use in at least one of a speech and an audio recognition is disclosed. The method comprises obtaining a first signal, wherein the first signal is at least one of a speech and an audio signal, modifying the first signal to obtain at least one second signal, dividing the first signal and the at least one second signal respectively into a plurality of first patches and a plurality of second patches, wherein each one of the plurality of first patches comprises a respective part of the first signal and each one of the plurality of second patches comprises a respective part of the at least one second signal and mixing selected ones of the plurality of first patches and the plurality of second patches to obtain a patched signal.
Inventors:
PESO PARADA PABLO (GB)
DOBROWOLSKA AGNIESZKA (GB)
SARAVANAN KARTHIKEYAN (GB)
OZAY METE (GB)
DOBROWOLSKA AGNIESZKA (GB)
SARAVANAN KARTHIKEYAN (GB)
OZAY METE (GB)
Application Number:
PCT/KR2023/002236
Publication Date:
September 21, 2023
Filing Date:
February 16, 2023
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G10L15/06; G10L15/20; G10L17/02; G10L17/20
Foreign References:
| US8880410B2 | 2014-11-04 | |||
| US10014000B2 | 2018-07-03 | |||
| US20180367674A1 | 2018-12-20 | |||
| US20150170663A1 | 2015-06-18 | |||
| US20130090934A1 | 2013-04-11 |
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: