Title:
SPEAKER DIARIZATION WITH EARLY-STOP CLUSTERING
Document Type and Number:
WIPO Patent Application WO/2020/199013
Kind Code:
A1
Abstract:
A method and apparatus for speaker diarization with early-stop clustering, segmenting an audio stream into at least one speech segment (710), the audio stream comprising speeches from at least one speaker; clustering the at least one speech segment into a plurality of clusters (720), the number of the plurality of clusters being greater than the number of the at least one speaker; selecting, from the plurality of clusters, at least one cluster of the highest similarity (730), the number of the selected at least one cluster being equal to the number of the at least one speaker; establishing a speaker classification model based on the selected at least one cluster (740); and aligning, through the speaker classification model, speech frames in the audio stream to the at least one speaker (750).
Inventors:
CHEN LIPING (US)
SOONG KAO-PING (US)
SOONG KAO-PING (US)
Application Number:
PCT/CN2019/080617
Publication Date:
October 08, 2020
Filing Date:
March 29, 2019
Export Citation:
Assignee:
MICROSOFT TECHNOLOGY LICENSING LLC (US)
CHEN LIPING (CN)
SOONG KAO PING (CN)
CHEN LIPING (CN)
SOONG KAO PING (CN)
International Classes:
G10L15/00
Foreign References:
| US20150025887A1 | 2015-01-22 | |||
| US20110119060A1 | 2011-05-19 | |||
| CN103531198A | 2014-01-22 | |||
| CN107358945A | 2017-11-17 |
Other References:
See also references of EP 3948848A4
Attorney, Agent or Firm:
NTD PATENT & TRADEMARK AGENCY LTD. (CN)
Download PDF: