公开(公告)号：US09875739B2

公开(公告)日：2018-01-23

申请号：US15158959

申请日：2016-05-19

Applicant: Verint Systems Ltd.

Inventor： Omer Ziv ,  Ron Wein ,  Ido Shapira ,  Ran Achituv

IPC: G10L17/00 ,  G10L15/26 ,  G10L25/78 ,  G10L25/51 ,  G10L17/06

CPC classification number: G10L15/26 ,  G10L17/06 ,  G10L25/51 ,  G10L25/78 ,  G10L2025/783

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.

公开(公告)号：US20170206893A1

公开(公告)日：2017-07-20

申请号：US15473231

申请日：2017-03-29

Applicant: Verint Systems Ltd.

Inventor： Ran Achituv ,  Omer Ziv ,  Roni Romano ,  Ido Shapira ,  Daniel Baum

IPC: G10L15/07 ,  G10L15/01 ,  G10L15/14

Abstract: Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.

公开(公告)号：US20160343373A1

公开(公告)日：2016-11-24

申请号：US15158959

申请日：2016-05-19

Applicant: Verint Systems Ltd.

Inventor： Omer Ziv ,  Ron Wein ,  Ido Shapira ,  Ran Achituv

IPC: G10L15/26 ,  G10L25/51 ,  G10L25/78 ,  G10L17/06

CPC classification number: G10L15/26 ,  G10L17/06 ,  G10L25/51 ,  G10L25/78 ,  G10L2025/783

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.

Abstract translation: 分离音频文件中的扬声器的系统和方法，包括获取音频文件。 音频文件由转录服务器转录成至少一个文本文件。 在至少一个文本文件内识别均匀的语音段。 音频文件被分割成与所识别的同源语音片段对应的同质音频段。 音频文件的同质音频片段被分成第一扬声器音频文件和第二扬声器音频文件，第一扬声器音频文件和第二扬声器音频文件被转录以产生经过缩写的转录。

公开(公告)号：US20160217792A1

公开(公告)日：2016-07-28

申请号：US15006572

申请日：2016-01-26

Applicant: Verint Systems Ltd.

Inventor： Alex Gorodetski ,  Oana Sidi ,  Ron Wein ,  Ido Shapira

IPC: G10L17/20 ,  G10L17/16 ,  G10L15/06 ,  G10L25/84 ,  G10L15/04 ,  G10L17/04 ,  G10L17/02

CPC classification number: G10L17/04 ,  G10L15/26 ,  G10L17/02 ,  G10L17/16 ,  G10L25/84

Abstract: Disclosed herein are methods of diarizing audio data using first-pass blind diarization and second-pass blind diarization that generate speaker statistical models, wherein the first pass-blind diarization is on a per-frame basis and the second pass-blind diarization is on a per-word basis, and methods of creating acoustic signatures for a common speaker based only on the statistical models of the speakers in each audio session.

Abstract translation: 这里公开的是使用第一遍盲目校正和产生说话者统计模型的二次盲目校正对音频数据进行着色的方法，其中第一次盲盲二值化处于每帧的基础上，而第二次盲目校正位于 每个单词基础的方法，以及仅基于每个音频会话中的扬声器的统计模型为公共扬声器创建声学签名的方法。

公开(公告)号：US20140074467A1

公开(公告)日：2014-03-13

申请号：US14016783

申请日：2013-09-03

Applicant: Verint Systems Ltd.

Inventor： Omer Ziv ,  Ron Wein ,  Ido Shapira ,  Ran Achituv

IPC: G10L15/26

CPC classification number: G10L15/26 ,  G10L17/06 ,  G10L25/51 ,  G10L25/78 ,  G10L2025/783

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.

Abstract translation: 分离音频文件中的扬声器的系统和方法，包括获取音频文件。 音频文件由转录服务器转录成至少一个文本文件。 在至少一个文本文件内识别均匀的语音段。 音频文件被分割成与所识别的同源语音片段对应的同质音频段。 音频文件的同质音频片段被分成第一扬声器音频文件和第二扬声器音频文件，第一扬声器音频文件和第二扬声器音频文件被转录以产生经过缩小的转录。