Patent · US Active

Speaker separation in diarization

US9368116B2 · kind B2 · utility

19Cited by

1References

15Claims

0Family size

Assignee

VERINT SYSTEMS INC. · IL

Inventors

Omer Ziv · Ramat Gan, IL
Ron Wein · Ramat HaSharon, IL
Ido Shapira · Nes Ziona, IL
Ran Achituv · Hod HaSharon, IL

Key dates

Filing date	Sep 3, 2013
Grant date	Jun 14, 2016
Priority date	—
Expiry date	Jun 3, 2034

Classification

Technology area (CPC G)Physics
CPC primaryG10L2025/783
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The system and method of separating speakers in an audio file including obtaining an audio file. The audio file is transcribed into at least one text file by a transcription server. Homogenous speech segments are identified within the at least one text file. The audio file is segmented into homogenous audio segments that correspond to the identified homogenous speech segments. The homogenous audio segments of the audio file are separated into a first speaker audio file and second speaker audio file the first speaker audio file and the second speaker audio file are transcribed to produce a diarized transcript.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.