Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND APPARATUS FOR PROCESSING VOICE DATA OF SPEECH
Document Type and Number:
WIPO Patent Application WO/2020/106103
Kind Code:
A1
Abstract:
A method and apparatus for processing voice data of a speech received from a speaker are provided. The method includes extracting a speaker feature vector from the voice data of the speech received from a speaker, generating a speaker feature map by positioning the extracted speaker feature vector at a specific position on a multi-dimensional vector space, forming a plurality of clusters indicating features of voices of a plurality of speakers by grouping at least one speaker feature vector positioned on the speaker feature map, and classifying the plurality of speakers according to the plurality of clusters.

Inventors:
ROH JAEYOUNG (KR)
CHO KEUNSEOK (KR)
HYUNG JIWON (KR)
JANG DONGHAN (KR)
LEE JAEWON (KR)
Application Number:
PCT/KR2019/016152
Publication Date:
May 28, 2020
Filing Date:
November 22, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G10L17/02; G10L15/04; G10L17/14; G10L17/18; G10L25/15; G16H50/30
Domestic Patent References:
WO2018201688A12018-11-08
Foreign References:
US20050182626A12005-08-18
US20040260550A12004-12-23
US20170053644A12017-02-23
Other References:
MAXIME JUMELLE ET AL.: "Speaker Clustering With Neural Networks And Audio Processing", ARXIV:1803.08276V1, 22 March 2018 (2018-03-22), pages 1 - 7, XP080861868, Retrieved from the Internet [retrieved on 20200305]
MAXIME JUMELLE ET AL., SPEAKER CLUSTERING WITH NEURAL NETWORKS AND AUDIO PROCESSING, 22 March 2018 (2018-03-22)
ELIE KHOURY ET AL., HIERARCHICAL SPEAKER CLUSTERING METHODS FOR THE NIST I-VECTOR CHALLENGE, 16 June 2014 (2014-06-16)
See also references of EP 3857546A4
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: