-
公开(公告)号：US09992448B2
公开(公告)日：2018-06-05
申请号：US15602127
申请日：2017-05-23
Applicant: Gong I.O Ltd.
Inventor： Eilon Reshef , Amit Bendov
IPC: H04N7/15 , H04N7/14 , G06F3/0484 , H04L29/06
CPC classification number: H04N7/147 , G06F3/0484 , H04L65/1089 , H04L65/4015 , H04L65/403 , H04N7/15 , H04N7/155
Abstract: Conference recording is carried out by identifying a virtual conference operated by a conferencing system connected to a communications network. A virtual participant process executing in a processor is registered with the conferencing system as a co-participant in the virtual conference. Information streams produced by the human participants are recorded and distributed with the virtual participant process.
-
公开(公告)号：US20180249122A1
公开(公告)日：2018-08-30
申请号：US15965929
申请日：2018-04-29
Applicant: GONG I.O LTD.
Inventor： Eilon Reshef , Amit Bendov
IPC: H04N7/14 , H04L29/06 , G06F3/0484 , H04N7/15
CPC classification number: H04N7/147 , G06F3/0484 , H04L65/1089 , H04L65/4015 , H04L65/403 , H04M3/527 , H04M3/563 , H04N7/15 , H04N7/155
Abstract: Conference recording is carried out by identifying a virtual conference operated by a conferencing system connected to a communications network. A virtual participant process executing in a processor is registered with the conferencing system as a co-participant in the virtual conference. Information streams produced by the human participants are recorded and distributed with the virtual participant process.
-
Patent Agency Ranking
公开(公告)号：US20180239822A1
公开(公告)日：2018-08-23
申请号：US15834090
申请日：2017-12-07
Applicant: GONG I.O Ltd.
Inventor： Eilon Reshef , Zvi Marx
CPC classification number: G06F16/61 , G06F16/685 , G06F17/271 , G06F17/2735 , G06F17/277 , G06F17/279 , G06N5/022 , G06N7/005 , G06N20/00 , G10L15/04 , G10L15/1815 , G10L15/26
Abstract: A method for information processing includes receiving in a computer a corpus of recorded conversations, with two or more speakers participating in each conversation. Respective frequencies of occurrence of multiple words in each of a plurality of chunks in each of the recorded conversations are computed. Based on the frequencies of occurrence of the words over the conversations in the corpus, an optimal set of topics to which the chunks can be assigned is derived, such that the optimal set maximizes a likelihood that the chunks will be generated by the topics in the set. A recorded conversation from the corpus is segmented using the derived topics into a plurality of segments, such that each segment is classified as belonging to a particular topic in the optimal set.
-
公开(公告)号：US11276407B2
公开(公告)日：2022-03-15
申请号：US16297757
申请日：2019-03-11
Applicant: GONG I.O LTD.
Inventor： Eilon Reshef , Hanan Shteingart , Zohar Shay
Abstract: A method for audio processing includes receiving, in a computer, a recording of a teleconference among multiple participants over a network including an audio stream containing speech uttered by the participants and conference metadata for controlling a display on video screens viewed by the participants during the teleconference. The audio stream is processed by the computer to identify speech segments, in which one or more of the participants were speaking, interspersed with intervals of silence in the audio stream. The conference metadata are parsed so as to extract speaker identifications, which are indicative of the participants who spoke during successive periods of the teleconference. The teleconference is diarized by labeling the identified speech segments from the audio stream with the speaker identifications extracted from corresponding periods of the teleconference.
-
公开(公告)号：US20210027772A1
公开(公告)日：2021-01-28
申请号：US16520374
申请日：2019-07-24
Applicant: GONG I.O LTD.
Inventor： Inbal Horev , Eilon Reshef , Omri Allouche , Yoav Madorsky , Hanan Shteingart
IPC: G10L15/197 , G10L15/04 , G10L15/22 , G10L21/10 , G06F16/2455
Abstract: A method for information processing includes completing, over a corpus of conversations, a conversation structure model including (i) a sequence of conversation parts having a defined order, and (ii) a probabilistic model defining each of the conversation parts. For a given conversation, a segmentation of the conversation is computed based on the computed conversation structure model. Action is taken on the given conversation according to the segmentation.
-
公开(公告)号：US20190318743A1
公开(公告)日：2019-10-17
申请号：US16297757
申请日：2019-03-11
Applicant: GONG I.O LTD.
Inventor： Eilon Reshef , Hanan Shteingart , Zohar Shay
Abstract: A method for audio processing includes receiving, in a computer, a recording of a teleconference among multiple participants over a network including an audio stream containing speech uttered by the participants and conference metadata for controlling a display on video screens viewed by the participants during the teleconference. The audio stream is processed by the computer to identify speech segments, in which one or more of the participants were speaking, interspersed with intervals of silence in the audio stream. The conference metadata are parsed so as to extract speaker identifications, which are indicative of the participants who spoke during successive periods of the teleconference. The teleconference is diarized by labeling the identified speech segments from the audio stream with the speaker identifications extracted from corresponding periods of the teleconference.
-
公开(公告)号：US20170257598A1
公开(公告)日：2017-09-07
申请号：US15602127
申请日：2017-05-23
Applicant: Gong I.O Ltd.
Inventor： Eilon Reshef , Amit Bendov
IPC: H04N7/14
CPC classification number: H04N7/147 , G06F3/0484 , H04L65/1089 , H04L65/4015 , H04L65/403 , H04N7/15 , H04N7/155
Abstract: Conference recording is carried out by identifying a virtual conference operated by a conferencing system connected to a communications network. A virtual participant process executing in a processor is registered with the conferencing system as a co-participant in the virtual conference. Information streams produced by the human participants are recorded and distributed with the virtual participant process.
-
-
-
-
-
-
Search Results
7
records
(took 0.011 seconds)
