-
1.发明申请公开(公告)号：US20180151174A1
公开(公告)日：2018-05-31
申请号：US15882958
申请日：2018-01-29
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
CPC classification number: G10L15/04 , G10L15/26 , G10L17/00 , G10L17/005 , G10L21/00 , G10L21/02 , H04L9/3231 , H04L2209/04 , H04L2209/56
Abstract: A system and method for identifying special information within a voice recording is provided. Training to identify a speaker is performed. A voice recording including utterances by at least two speakers is processed to identify segments of the voice recording provided by the speaker. Remaining segments of the voice recording are designated as provided by another speaker. A text element that corresponds to a request for information is identified in at least one of the segments of the voice recording provided by the speaker. A predetermined duration associated with the identified text element is applied to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element. The utterances from the other speaker occurring within the predetermined duration are identified as special information and rendered unintelligible.
-
Patent Agency Ranking
公开(公告)号：US08954332B2
公开(公告)日：2015-02-10
申请号：US14071639
申请日：2013-11-04
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
CPC classification number: G10L15/04 , G10L15/26 , G10L17/00 , G10L17/005 , G10L21/00 , G10L21/02 , H04L9/3231 , H04L2209/04 , H04L2209/56
Abstract: A computer-implemented system and method for masking special data is provided. Speakers of a call recording are identified. The call recording is separated into strands corresponding to each of the speakers. A prompt list of elements that prompt the speaker of the other strand to utter special information is applied to one of the strands. At least one of the elements of the prompt list is identified in the one strand. A special information candidate is identified in the other strand and is located after a location in time where the element was found in the voice recording of the one strand. A confidence score is assigned to the element located in the one strand and to the special information candidate in the other strand. The confidence scores are combined and a threshold is applied. The special information candidate is rendered unintelligible when the combined confidence scores satisfy the threshold.
Abstract translation: 提供了一种用于屏蔽特殊数据的计算机实现的系统和方法。 确定了通话记录的扬声器。 呼叫记录被分成与每个扬声器对应的线。 提示其他线索的扬声器发出特殊信息的元素的提示列表应用于其中一条线。 提示列表的至少一个元素在一条链中被识别。 在另一条链中识别出特殊信息候选者，并且位于在一条链的录音中发现该元素的时间点之后。 信任分数被分配给位于一条链中的元素和另一条链中的特殊信息候选。 组合置信度得分并应用阈值。 当组合的置信分数满足阈值时，特殊信息候选者变得难以理解。
-
公开(公告)号：US20150302849A1
公开(公告)日：2015-10-22
申请号：US14617823
申请日：2015-02-09
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
CPC classification number: G10L15/04 , G10L15/26 , G10L17/00 , G10L17/005 , G10L21/00 , G10L21/02 , H04L9/3231 , H04L2209/04 , H04L2209/56
Abstract: A system and method for identifying special information is provided. Endpoints are defined within a voice recording. One or more of the endpoints are identified within the voice recording and the voice recording is partitioned into segments based on the identified endpoints. Elements of text are identified by applying speech recognition to each of the segments and a list of prompt list candidates are applied to the text elements. The segments with text elements that match one or more prompt list candidates are identified. Portions of the voice recording following the prompt list candidates that include special information are identified and the special information is rendered unintelligible within the voice recording.
Abstract translation: 提供了一种用于识别特殊信息的系统和方法。 端点在录音内定义。 在语音记录中识别一个或多个端点，并且基于所识别的端点将语音记录划分成段。 通过将语音识别应用于每个段来标识文本的元素，并且将提示列表候选列表应用于文本元素。 识别具有与一个或多个提示列表候选者匹配的文本元素的段。 识别包含特殊信息的提示列表候选之后的语音记录的部分，并且在语音记录中使特殊信息变得难以理解。
-
公开(公告)号：US20140129219A1
公开(公告)日：2014-05-08
申请号：US14071639
申请日：2013-11-04
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
IPC: G10L17/00
CPC classification number: G10L15/04 , G10L15/26 , G10L17/00 , G10L17/005 , G10L21/00 , G10L21/02 , H04L9/3231 , H04L2209/04 , H04L2209/56
Abstract: A computer-implemented system and method for masking special data is provided. Speakers of a call recording are identified. The call recording is separated into strands corresponding to each of the speakers. A prompt list of elements that prompt the speaker of the other strand to utter special information is applied to one of the strands. At least one of the elements of the prompt list is identified in the one strand. A special information candidate is identified in the other strand and is located after a location in time where the element was found in the voice recording of the one strand. A confidence score is assigned to the element located in the one strand and to the special information candidate in the other strand. The confidence scores are combined and a threshold is applied. The special information candidate is rendered unintelligible when the combined confidence scores satisfy the threshold.
Abstract translation: 提供了一种用于屏蔽特殊数据的计算机实现的系统和方法。 确定了通话记录的扬声器。 呼叫记录被分成与每个扬声器对应的线。 提示其他线索的扬声器发出特殊信息的元素的提示列表应用于其中一条线。 提示列表的至少一个元素在一条链中被识别。 在另一条链中识别出特殊信息候选者，并且位于在一条链的录音中发现该元素的时间点之后。 信任分数被分配给位于一条链中的元素和另一条链中的特殊信息候选。 组合置信度得分并应用阈值。 当组合的置信分数满足阈值时，特殊信息候选者变得难以理解。
-
5.发明授权公开(公告)号：US10446134B2
公开(公告)日：2019-10-15
申请号：US15882958
申请日：2018-01-29
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
Abstract: A system and method for identifying special information within a voice recording is provided. Training to identify a speaker is performed. A voice recording including utterances by at least two speakers is processed to identify segments of the voice recording provided by the speaker. Remaining segments of the voice recording are designated as provided by another speaker. A text element that corresponds to a request for information is identified in at least one of the segments of the voice recording provided by the speaker. A predetermined duration associated with the identified text element is applied to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element. The utterances from the other speaker occurring within the predetermined duration are identified as special information and rendered unintelligible.
-
公开(公告)号：US09881604B2
公开(公告)日：2018-01-30
申请号：US14617823
申请日：2015-02-09
Applicant: Intellisist, Inc.
Inventor： Howard M. Lee , Steven Lutz , Gilad Odinak
CPC classification number: G10L15/04 , G10L15/26 , G10L17/00 , G10L17/005 , G10L21/00 , G10L21/02 , H04L9/3231 , H04L2209/04 , H04L2209/56
Abstract: A system and method for identifying special information is provided. Endpoints are defined within a voice recording. One or more of the endpoints are identified within the voice recording and the voice recording is partitioned into segments based on the identified endpoints. Elements of text are identified by applying speech recognition to each of the segments and a list of prompt list candidates are applied to the text elements. The segments with text elements that match one or more prompt list candidates are identified. Portions of the voice recording following the prompt list candidates that include special information are identified and the special information is rendered unintelligible within the voice recording.
-
-
-
-
-
Search Results
6
records
(took 0.011 seconds)
