-
公开(公告)号：US09881617B2
公开(公告)日：2018-01-30
申请号：US15254326
申请日：2016-09-01
Applicant: Verint Systems Ltd.
IPC: G10L15/26 , G10L17/06 , G10L17/02 , G10L17/16 , G10L15/02 , G10L17/04 , G10L25/78 , H04M3/51 , G10L15/00
CPC classification number: G10L17/06 , G10L15/02 , G10L15/26 , G10L17/02 , G10L17/04 , G10L17/16 , G10L25/78 , G10L2015/025 , H04M3/5175 , H04M2201/41 , H04M2203/303
Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.
-
公开(公告)号：US09875742B2
公开(公告)日：2018-01-23
申请号：US15006572
申请日：2016-01-26
Applicant: Verint Systems Ltd.
Inventor： Alex Gorodetski , Oana Sidi , Ron Wein , Ido Shapira
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.
-
13.发明申请公开(公告)号：US20170053653A1
公开(公告)日：2017-02-23
申请号：US15254326
申请日：2016-09-01
Applicant: Verint Systems Ltd.
CPC classification number: G10L17/06 , G10L15/02 , G10L15/26 , G10L17/02 , G10L17/04 , G10L17/16 , G10L25/78 , G10L2015/025 , H04M3/5175 , H04M2201/41 , H04M2203/303
Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.
Abstract translation: 在音频数据的分类方法中，将音频数据分割为多个话语。 每个话语被表示为代表多个特征向量的话语模型。 话语模型是聚类的。 从群集话语模型构建多个说话者模型。 由多个扬声器模型构成隐马尔可夫模型。 已识别的扬声器模型的序列被解码。
-
公开(公告)号：US20150025887A1
公开(公告)日：2015-01-22
申请号：US14319860
申请日：2014-06-30
Applicant: VERINT SYSTEMS LTD.
IPC: G10L15/06
CPC classification number: G10L17/06 , G10L15/02 , G10L15/26 , G10L17/02 , G10L17/04 , G10L17/16 , G10L25/78 , G10L2015/025 , H04M3/5175 , H04M2201/41 , H04M2203/303
Abstract: In a method of diarization of audio data, audio data is segmented into a plurality of utterances. Each utterance is represented as an utterance model representative of a plurality of feature vectors. The utterance models are clustered. A plurality of speaker models are constructed from the clustered utterance models. A hidden Markov model is constructed of the plurality of speaker models. A sequence of identified speaker models is decoded.
Abstract translation: 在音频数据的分类方法中，将音频数据分割为多个话语。 每个话语被表示为代表多个特征向量的话语模型。 话语模型是聚类的。 从群集话语模型构建多个说话者模型。 由多个扬声器模型构成隐马尔可夫模型。 已识别的扬声器模型的序列被解码。
-
公开(公告)号：US11636860B2
公开(公告)日：2023-04-25
申请号：US16934455
申请日：2020-07-21
Applicant: Verint Systems Ltd.
Inventor： Alex Gorodetski , Oana Sidi , Ron Wein , Ido Shapira
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.
-
Patent Agency Ranking
公开(公告)号：US20210224483A1
公开(公告)日：2021-07-22
申请号：US17225589
申请日：2021-04-08
Applicant: Verint Systems Ltd.
Inventor： Daniel Baum , Uri Segal , Ron Wein , Oana Sidi
IPC: G06F40/289 , G06F16/36 , G06F40/284
Abstract: A method for expanding an initial ontology via processing of communication data, wherein the initial ontology is a structural representation of language elements comprising a set of entities, a set of terms, a set of term-entity associations, a set of entity-association rules, a set of abstract relations, and a set of relation instances. A method for extracting a set of significant phrases and a set of significant phrase co-occurrences from an input set of documents further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another.
-
公开(公告)号：US20200349956A1
公开(公告)日：2020-11-05
申请号：US16934455
申请日：2020-07-21
Applicant: Verint Systems Ltd.
Inventor： Alex Gorodetski , Oana Sidi , Ron Wein , Ido Shapira
IPC: G10L17/04
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.
-
公开(公告)号：US10726848B2
公开(公告)日：2020-07-28
申请号：US15876778
申请日：2018-01-22
Applicant: Verint Systems Ltd.
Inventor： Alex Gorodetski , Oana Sidi , Ron Wein , Ido Shapira
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.
-
公开(公告)号：US20180211670A1
公开(公告)日：2018-07-26
申请号：US15876534
申请日：2018-01-22
Applicant: Verint Systems Ltd.
Inventor： Alex Gorodetski , Ido Shapira , Ron Wein , Oana Sidi
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.
-
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
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.
-
-
-
-
-
-
-
-
-
Search Results
48
records
(took 0.046 seconds)
