Papers published on a yearly basis
Papers
More filters
•
25 Mar 2014TL;DR: In this article, a method for adapting a language model for a context of a domain, comprising obtaining textual contents from a large source by a request directed to the context of the domain, discarding at least a part of the textual contents that contain textual terms determined as irrelevant or irrelevant to the domain context, and retaining, as retained data, the remaining textual terms that are determined as relevant or relevant.
Abstract: A method for adapting a language model for a context of a domain, comprising obtaining textual contents from a large source by a request directed to the context of the domain, discarding at least a part of the textual contents that contain textual terms determined as irrelevant to the context of the domain, thereby retaining, as retained data, at least a part of the textual contents that contain textual terms determined as relevant to the context of the domain, and adapting the language model by incorporating therein at least a part of the textual terms of the retained data, wherein the method is performed on an at least one computerized apparatus configured to perform the method and equipped for communication with the large source, and an apparatus for performing the same.
10 citations
•
30 Sep 2015TL;DR: In this article, a system and method for improving a phrase spotting score is described, which may include providing a test speech and a transcription thereof, obtaining an input phrases in a textual form for spotting in the provided test speech, and applying a classifying model to the phonetic transcription of the test speech according to a posterior probability feature and to a set of phrase spotting features related to the input phrase.
Abstract: Embodiments of the disclosed subject matter include a system and method for improving a phrase spotting score The method may include providing a test speech and a transcription thereof, obtaining an input phrases in a textual form for spotting in the provided test speech, generating a phonetic transcription for the input phrase, and applying a classifying model to the phonetic transcription of the test speech according to a posterior probability feature and to a set of phrase spotting features related to the input phrase, the phrase spotting features selected from features extracted from a decoding process of the phrase, context-based features, and/or a combination thereof, thereby spotting the given phrase with a confidence score The classifying model is priorly trained for spotting the input phrase according to the posterior probability feature and to the plurality of phrase spotting features
9 citations
•
12 Nov 2002TL;DR: In this article, a system for recording and/or monitoring data, by forwarding it without analysing or otherwise filtering the data itself, comprises a communication subsystem 52, including a management unit 59, and a recording/monitoring subsystem 62.
Abstract: A system for recording and/or monitoring data, by forwarding it without analysing or otherwise filtering the data itself, comprises a communication subsystem 52, including a management unit 59, and a recording/monitoring subsystem 62. The communication subsystem arranges for session data between at least two parties 58,56 to be forwarded to the recording/monitoring subsystem in accordance with rules. The rules may be dynamic, static, deterministic, statistical or event driven and may be set to include consideration of the session's metadata (eg session identifiers such as extension identifiers or telephone numbers). The parties may communicate session data relating to relating to Voice over IP (VoIP) or multimedia such as video conferencing, chat, web collaboration, application sharing, trunk radio or any other data capable of being logged and monitored. The parties' communication devices may be arranged to duplicate their data packets for forwarding to the monitoring device as well as other parties. The Communication subsystem 52's rules may be remotely configured via an external API (application programming interface). A specific embodiment relates to the recording of a VoIP call by joining a recording device (24, fig. 1) in conference with the parties to the call.
9 citations
•
16 Dec 2010TL;DR: In this article, the authors propose a method for spotting an interaction in which a target speaker associated with a current index or current interaction speaks, the method comprising: receiving an interaction and an index associated with the interaction, the index associated associated with additional data; receiving the current interaction or current indexassociated with the target speaker; obtaining current data associated with current interaction and current index; filtering the index using the additional data, and obtaining a matching index.
Abstract: A method for spotting an interaction in which a target speaker associated with a current index or current interaction speaks, the method comprising: receiving an interaction and an index associated with the interaction, the index associated with additional data; receiving the current interaction or current index associated with the target speaker; obtaining current data associated with the current interaction or current index; filtering the index using the additional data, in accordance with the current data associated with the current interaction or current index, and obtaining a matching index; and comparing the current index or a representation of the current interaction with the matching index to obtain a target speaker index.
8 citations
•
02 Oct 2014TL;DR: In this article, an orthogonal transformation on a corresponding pair of blocks in the video image and the reference image is performed, and an infinity-norm difference between the coefficient values of the corresponding pairs of transformed and modified blocks is determined and compared to a threshold.
Abstract: A system and method for detecting change in a video stream may include receiving, by a processor, a video image from a video stream and a reference image. The processor may divide the video image and the reference image into non-overlapping blocks, and each block in the video image may correspond to a block in the reference image. The processor may perform an orthogonal transformation on a corresponding pair of blocks in the video image and the reference image. DC (direct current, or, average value) components in the orthogonally transformed pair of blocks in the video image and the reference image may be zeroed. An infinity-norm difference between coefficient values of the corresponding pair of transformed and modified blocks in the video image and the reference image may be determined and compared to a threshold.
8 citations
Authors
Showing all 277 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yaniv Zigel | 21 | 79 | 2170 |
Moshe Wasserblat | 21 | 31 | 1164 |
Oren Pereg | 20 | 31 | 1674 |
J. D. McFall | 19 | 25 | 1862 |
Eyal Kolman | 12 | 38 | 450 |
Moshe Levin | 12 | 28 | 602 |
Yuval Lubowich | 12 | 16 | 529 |
Leon Portman | 11 | 17 | 438 |
Dan Eylon | 11 | 15 | 777 |
Ezra Daya | 10 | 14 | 320 |
Eran Halbraich | 9 | 10 | 290 |
Igal Dvir | 8 | 13 | 902 |
Moshe Wasserblat | 8 | 30 | 491 |
Ronen Laperdon | 8 | 8 | 224 |
Yaniv Gurwicz | 8 | 18 | 215 |