Patents by Inventor Ran Achituv
Ran Achituv has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10134401Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: GrantFiled: November 20, 2013Date of Patent: November 20, 2018Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 10134400Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: GrantFiled: November 20, 2013Date of Patent: November 20, 2018Assignee: Verint Systems Ltd.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 9990920Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.Type: GrantFiled: October 24, 2016Date of Patent: June 5, 2018Assignee: VERINT SYSTEMS LTD.Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
-
Patent number: 9875739Abstract: 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.Type: GrantFiled: May 19, 2016Date of Patent: January 23, 2018Assignee: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ron Wein, Ido Shapira, Ran Achituv
-
Publication number: 20170206893Abstract: 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.Type: ApplicationFiled: March 29, 2017Publication date: July 20, 2017Applicant: Verint Systems Ltd.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Patent number: 9633650Abstract: 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.Type: GrantFiled: May 30, 2014Date of Patent: April 25, 2017Assignee: Verint Systems Ltd.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Publication number: 20170098445Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio tile transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio tile transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.Type: ApplicationFiled: October 24, 2016Publication date: April 6, 2017Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
-
Patent number: 9508346Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.Type: GrantFiled: May 30, 2014Date of Patent: November 29, 2016Assignee: VERINT SYSTEMS LTD.Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
-
Publication number: 20160343373Abstract: 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.Type: ApplicationFiled: May 19, 2016Publication date: November 24, 2016Inventors: Omer Ziv, Ron Wein, Ido Shapira, Ran Achituv
-
Patent number: 9401145Abstract: A method for converting speech to text in a speech analytics system is provided. The method includes receiving audio data containing speech made up of sounds from an audio source, processing the sounds with a phonetic module resulting in symbols corresponding to the sounds, and processing the symbols with a language module and occurrence table resulting in text. The method also includes determining a probability of correct translation for each word in the text, comparing the probability of correct translation for each word in the text to the occurrence table, and adjusting the occurrence table based on the probability of correct translation for each word in the text.Type: GrantFiled: May 5, 2014Date of Patent: July 26, 2016Assignee: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ran Achituv, Ido Shapira
-
Patent number: 9368116Abstract: 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.Type: GrantFiled: September 3, 2013Date of Patent: June 14, 2016Assignee: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ron Wein, Ido Shapira, Ran Achituv
-
Publication number: 20150066502Abstract: 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.Type: ApplicationFiled: May 30, 2014Publication date: March 5, 2015Applicant: Verint Systems Ltd.Inventors: Ran Achituv, Omer Ziv, Roni Romano, Ido Shapira, Daniel Baum
-
Publication number: 20150066503Abstract: Systems and methods of automated adaptation of a language model for transcription of audio data include obtaining audio data. The audio data is transcribed with a language model to produce a plurality of audio file transcriptions. A quality of the plurality of audio file transcriptions is evaluated. At least one best transcription from a plurality of audio file transcriptions is selected based upon the evaluated quality. Statistics are calculated from the selected at least one best transcription from the plurality of audio file transcriptions. The language model is modified from the calculated statistics.Type: ApplicationFiled: May 30, 2014Publication date: March 5, 2015Applicant: VERINT SYSTEMS LTD.Inventors: Ran Achituv, Omer Ziv, Ido Shapira, Daniel Baum
-
Publication number: 20140142944Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.Type: ApplicationFiled: November 20, 2013Publication date: May 22, 2014Applicant: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Publication number: 20140142940Abstract: Systems and methods of diarization using linguistic labeling include receiving a set of diarized textual transcripts. A least one heuristic is automatedly applied to the diarized textual transcripts to select transcripts likely to be associated with an identified group of speakers. The selected transcripts are analyzed to create at least one linguistic model. The linguistic model is applied to transcripted audio data to label a portion of the transcripted audio data as having been spoken by the identified group of speakers. Still further embodiments of diarization using linguistic labeling may serve to label agent speech and customer speech in a recorded and transcripted customer service interaction.Type: ApplicationFiled: November 20, 2013Publication date: May 22, 2014Applicant: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ran Achituv, Ido Shapira, Jeremie Dreyfuss
-
Patent number: 8719016Abstract: A method for converting speech to text in a speech analytics system is provided. The method includes receiving audio data containing speech made up of sounds from an audio source, processing the sounds with a phonetic module resulting in symbols corresponding to the sounds, and processing the symbols with a language module and occurrence table resulting in text. The method also includes determining a probability of correct translation for each word in the text, comparing the probability of correct translation for each word in the text to the occurrence table, and adjusting the occurrence table based on the probability of correct translation for each word in the text.Type: GrantFiled: April 7, 2010Date of Patent: May 6, 2014Assignee: Verint Americas Inc.Inventors: Omer Ziv, Ran Achituv, Ido Shapira
-
Publication number: 20140074467Abstract: 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.Type: ApplicationFiled: September 3, 2013Publication date: March 13, 2014Applicant: VERINT SYSTEMS LTD.Inventors: Omer Ziv, Ron Wein, Ido Shapira, Ran Achituv
-
Publication number: 20100142549Abstract: A computer-implemented method for data recording includes defining a rule, the rule identifying data items exchanged between an originating endpoint and a recipient endpoint over a communication network, having nodes, as target data items for storage by a storage device. The storage device has a communication address. A node of the communication network is configured with the rule and with the communication address of the storage device. The rule causes the node to recognize the target data items while forwarding the data items between the originating and recipient endpoints and to forward respective copies of the recognized target data items to the communication address of the storage device.Type: ApplicationFiled: January 9, 2009Publication date: June 10, 2010Inventors: Ran Achituv, Shai Levi
-
Publication number: 20080208579Abstract: A computer-implemented method for session processing includes identifying a type of data item that is presented to a user by a computerized system. A session in which the user interacts with the computerized system is recorded. A data item of the identified type is automatically detected in the recorded session. The recorded session is replayed, while refraining from presenting the detected data item in the replayed session.Type: ApplicationFiled: February 27, 2007Publication date: August 28, 2008Inventors: Brian Weiss, Ran Achituv, David Bruce, Shai Levi, Ariel Shemesh, Saar Carmi, Arie Zaks