公开(公告)号：US20110004473A1

公开(公告)日：2011-01-06

申请号：US12497718

申请日：2009-07-06

申请人： Ronen Laperdon ,  Moshe Wasserblat ,  Shimrit Artzi ,  Yuval Lubowich

发明人： Ronen Laperdon ,  Moshe Wasserblat ,  Shimrit Artzi ,  Yuval Lubowich

IPC分类号： G10L15/06 ,  G10L15/04 ,  G10L17/00 ,  G06F17/30

CPC分类号： G10L15/02 ,  G10L2015/025

摘要： A method and apparatus for improving speech recognition results for an audio signal captured within an organization, comprising: receiving the audio signal captured by a capturing or logging device; extracting a phonetic feature and an acoustic feature from the audio signal; decoding the phonetic feature into a phonetic searchable structure; storing the phonetic searchable structure and the acoustic feature in an index; performing phonetic search for a word or a phrase in the phonetic searchable structure to obtain a result; activating an audio analysis engine which receives the acoustic feature to validate the result and obtain an enhanced result.

摘要翻译： 一种用于改善在组织内捕获的音频信号的语音识别结果的方法和装置，包括：接收由捕获或记录装置捕获的音频信号; 从音频信号中提取语音特征和声学特征; 将语音特征解码成语音可搜索结构; 将语音可搜索结构和声学特征存储在索引中; 在语音搜索结构中执行语音搜索单词或短语以获得结果; 激活音频分析引擎，其接收声学特征以验证结果并获得增强的结果。

公开(公告)号：US09015046B2

公开(公告)日：2015-04-21

申请号：US12797618

申请日：2010-06-10

申请人： Oren Pereg ,  Moshe Wasserblat ,  Yuval Lubowich ,  Ronen Laperdon ,  Dori Shapira ,  Vladislav Feigin ,  Oz Fox-Kahana

发明人： Oren Pereg ,  Moshe Wasserblat ,  Yuval Lubowich ,  Ronen Laperdon ,  Dori Shapira ,  Vladislav Feigin ,  Oz Fox-Kahana

IPC分类号： G10L15/00 ,  G06Q10/06 ,  G10L15/08 ,  G10L15/22 ,  G06Q30/00 ,  G06Q30/02

CPC分类号： G06Q10/063 ,  G06Q30/01 ,  G06Q30/0202 ,  G10L15/08 ,  G10L15/22 ,  G10L2015/081 ,  G10L2015/085

摘要： A method and system for indicating in real time that an interaction is associated with a problem or issue, comprising: receiving a segment of an interaction in which a representative of the organization participates; extracting a feature from the segment; extracting a global feature associated with the interaction; aggregating the feature and the global feature; and classifying the segment or the interaction in association with the problem or issue by applying a model to the feature and the global feature. The method and system may also use features extracted from earlier segments within the interaction. The method and system can also evaluate the model based on features extracted from training interactions and manual tagging assigned to the interactions or segments thereof.

摘要翻译： 一种用于实时地指示交互与问题或问题相关联的方法和系统，包括：接收所述组织的代表参与的交互的一部分; 从段中提取特征; 提取与交互相关联的全局特征; 聚合特征和全局特征; 并通过将模型应用于特征和全局特征来分类或与问题或问题相关联的交互。 方法和系统还可以使用在交互作用中从先前段提取的特征。 该方法和系统还可以基于从训练相互作用提取的特征和分配给其相互作用或分段的手动标记来评估模型。

公开(公告)号：US09311914B2

公开(公告)日：2016-04-12

申请号：US13602214

申请日：2012-09-03

申请人： Moshe Wasserblat ,  Dan Eylon ,  Tzach Ashkenazi ,  Oren Pereg ,  Ronen Laperdon

发明人： Moshe Wasserblat ,  Dan Eylon ,  Tzach Ashkenazi ,  Oren Pereg ,  Ronen Laperdon

IPC分类号： G10L13/08 ,  G10L19/02 ,  G10L19/12 ,  G10L15/08 ,  G10L15/22 ,  G10L15/187 ,  G10L15/26 ,  G10L15/20 ,  G10L15/02 ,  G10L15/10 ,  G06F17/30 ,  G06F17/27 ,  G06Q10/10 ,  G10L15/04

CPC分类号： G10L15/02 ,  G10L15/04 ,  G10L2015/025

摘要： The subject matter discloses a method two phase phonetic indexing and search comprising: receiving a digital representation of an audio signal; producing a phonetic index of the audio signal; producing phonetic N-gram sequence from the phonetic index by segmenting the phonetic index into a plurality of phonetic N-grams; and producing an inverted index of the plurality of phonetic N-grams.

摘要翻译： 主题公开了一种方法两相语音索引和搜索，包括：接收音频信号的数字表示; 产生音频信号的语音索引; 通过将语音指数分割成多个语音N-gram从语音指数产生语音N-gram序列; 并产生多个语音N-gram的反向索引。

公开(公告)号：US08831947B2

公开(公告)日：2014-09-09

申请号：US12941057

申请日：2010-11-07

申请人： Moshe Wasserblat ,  Ronen Laperdon ,  Dori Shapira

发明人： Moshe Wasserblat ,  Ronen Laperdon ,  Dori Shapira

IPC分类号： G10L15/00 ,  G10L15/28 ,  G10L15/04 ,  G10L15/08

CPC分类号： G10L15/08

摘要： A method and apparatus combining the advantages of phonetic search such as the rapid implementation and deployment and medium accuracy, comprising steps and components for receiving the audio signal captured in the call center environment, extracting a multiplicity of feature vectors from the audio signal, creating a phoneme lattice from the multiplicity of feature vectors wherein the phoneme lattice comprising one or more allophone and each allophone comprising two or more phonemes, creating a hybrid phoneme-word lattice from the phoneme lattice and extracting the word by analyzing the hybrid phoneme-Word lattice.

摘要翻译： 一种结合语音搜索的优点的方法和装置，例如快速实现和部署以及中等精度，包括用于接收在呼叫中心环境中捕获的音频信号的步骤和组件，从音频信号中提取多个特征向量，创建一个 从多个特征向量的音素格子中，其中包括一个或多个异音素的音素晶格和包含两个或更多个音素的每个异音素，从音素晶格产生混合的音素单元格，并通过分析混合的音素-Word晶格提取单词。

公开(公告)号：US08676586B2

公开(公告)日：2014-03-18

申请号：US12211112

申请日：2008-09-16

申请人： Moshe Wasserblat ,  Oren Pereg ,  Yuval Lubowich

发明人： Moshe Wasserblat ,  Oren Pereg ,  Yuval Lubowich

IPC分类号： G10L21/00

CPC分类号： G10L15/18 ,  G10L15/02 ,  G10L25/48 ,  H04M3/5232

摘要： A method and apparatus for analyzing and segmenting a vocal interaction captured in a test audio source, the test audio source captured within an environment. The method and apparatus first use text and acoustic features extracted from the interaction with tagging information, for constructing a model. Then, at production time, text and acoustic features are extracted from the interactions, and by applying the model, tagging information is retrieved for the interaction, enabling analysis, flow visualization or further processing of the interaction.

摘要翻译： 一种用于分析和分割在测试音频源中捕获的声音交互的方法和装置，在环境中捕获的测试音频源。 该方法和装置首先使用从与标签信息的交互提取的文本和声学特征，用于构建模型。 然后，在生产时间，从交互中提取文本和声学特征，并通过应用模型，检索标签信息进行交互，实现分析，流程可视化或进一步处理交互。

公开(公告)号：US08311824B2

公开(公告)日：2012-11-13

申请号：US12258463

申请日：2008-10-27

申请人： Yuval Lubowich ,  Moshe Wasserblat ,  Dimitri Volsky ,  Oren Pereg

发明人： Yuval Lubowich ,  Moshe Wasserblat ,  Dimitri Volsky ,  Oren Pereg

IPC分类号： G10L15/26

CPC分类号： G10L15/005

摘要： In a multi-lingual environment, a method and apparatus for determining a language spoken in a speech utterance. The method and apparatus test acoustic feature vectors extracted from the utterances against acoustic models associated with one or more of the languages. Speech to text is then performed for the language indicated by the acoustic testing, followed by textual verification of the resulting text. During verification, the resulting text is processed by language specific NLP and verified against textual models associated with the language. The system is self-learning, i.e., once a language is verified or rejected, the relevant feature vectors are used for enhancing one or more acoustic models associated with one or more languages, so that acoustic determination may improve.

摘要翻译： 在多语言环境中，一种用于确定语音话语中所说的语言的方法和装置。 所述方法和装置测试从与一种或多种语言相关联的声学模型的话语中提取的声学特征向量。 然后对由声学测试指示的语言执行到文本的语音，然后对所得到的文本进行文本验证。 在验证期间，生成的文本由语言特定的NLP处理，并针对与该语言相关联的文本模型进行验证。 该系统是自学习的，即，一旦语言被验证或拒绝，相关的特征向量被用于增强与一种或多种语言相关联的一个或多个声学模型，使得声学测定可以改善。

公开(公告)号：US20090292541A1

公开(公告)日：2009-11-26

申请号：US12126884

申请日：2008-05-25

申请人： Ezra Daya ,  Oren Pereg ,  Yuval Lubowich ,  Moshe Wasserblat

发明人： Ezra Daya ,  Oren Pereg ,  Yuval Lubowich ,  Moshe Wasserblat

IPC分类号： G10L15/04

CPC分类号： G10L15/063 ,  G10L15/18 ,  G10L2015/088 ,  G10L2015/226

摘要： Methods and apparatus for the enhancement of speech to text engines, by providing indications to the correctness of the found words, based on additional sources besides the internal indication provided by the STT engine. The enhanced indications comprise sources of data such as acoustic features, CTI features, phonetic search and others. The apparatus and methods also enable the detection of important or significant keywords found in audio files, thus enabling more efficient usages, such as further processing or transfer of interactions to relevant agents, escalation of issues, or the like. The methods and apparatus employ a training phase in which word model and key phrase model are generated for determining an enhanced correctness indication for a word and an enhanced importance indication for a key phrase, based on the additional features.

摘要翻译： 除了STT引擎提供的内部指示之外，还可以通过提供对发现的词语的正确性的指示来增强语言到文本引擎的方法和装置。 增强的指示包括诸如声学特征，CTI特征，语音搜索等的数据源。 该装置和方法还能够检测在音频文件中发现的重要或重要的关键词，从而实现更有效的用途，例如进一步处理或转移相关代理人的交互，升级问题等。 所述方法和装置采用训练阶段，其中基于附加特征，生成词模型和密钥短语模型，用于确定词的增强正确性指示和关键短语的增强重要性指示。

公开(公告)号：US08145562B2

公开(公告)日：2012-03-27

申请号：US12399999

申请日：2009-03-09

申请人： Moshe Wasserblat ,  Yuval Lubowich

发明人： Moshe Wasserblat ,  Yuval Lubowich

IPC分类号： G06Q40/00

CPC分类号： G06Q40/02 ,  G06Q10/10 ,  G06Q40/00 ,  G06Q40/025

摘要： The disclosed method and apparatus combine interactions and transactions in order to detect fraud acts or fraud attempts. In one embodiment, one or more interactions is correlated with one or more transactions, the interactions is and transactions features are combined, and features are extracted from the combined structure. The features are compared against one or more profiles, and a combined risk score is determined for the interactions or transactions. If the risk score exceeds a predetermined threshold, a preventive/corrective action can be taken.In another embodiment, behavioral characteristics extracted from one or more interactions associated with a transaction, with a risk score obtained by analyzing the transaction. The behavioral characteristic are used to enhance suspicion level related to a transaction being fraudulent, and to enable the taking of measures related to the transaction or to the person handling the transaction. The combination thus enables better assessment whether a particular interaction or transaction is fraudulent, and therefore provides for better detection or prevention of such activities. In addition, making the fraud assessment more reliable enables more efficient resource allocation of personnel for monitoring the transactions and interactions, better usage of communication time by avoiding lengthy identification where not required, and generally higher efficiency.

摘要翻译： 所公开的方法和装置结合了交互和交易以便检测欺诈行为或欺诈尝试。 在一个实施例中，一个或多个交互与一个或多个交易相关联，交互是并且交易特征被组合，并且从组合结构中提取特征。 将功能与一个或多个配置文件进行比较，并确定交互或交易的组合风险分数。 如果风险分数超过预定阈值，则可采取预防/纠正措施。 在另一个实施例中，从与交易相关联的一个或多个交互中提取的行为特征，具有通过分析交易获得的风险评分。 行为特征用于提高与欺诈交易相关的怀疑水平，并且能够采取与交易相关的措施或处理交易的人。 因此，组合能够更好地评估特定交互或交易是否是欺诈性的，因此提供更好的检测或预防这些活动。 此外，使欺诈评估更可靠，可以更有效地进行人员资源分配，以监控交易和交互，避免通信时间的长时间避免冗长的识别，而且通常效率更高。

公开(公告)号：US20110307258A1

公开(公告)日：2011-12-15

申请号：US12815429

申请日：2010-06-15

申请人： Hadas Liberman ,  Keren Eshkol ,  Oren Lewkowicz ,  Omer Gazit ,  Zohar Tzfoni ,  Avi Revivo ,  Leon Portman ,  Ronit Ephrat ,  Oren Pereg ,  Ronen Laperdon ,  Dori Shapira ,  Moshe Wasserblat

发明人： Hadas Liberman ,  Keren Eshkol ,  Oren Lewkowicz ,  Omer Gazit ,  Zohar Tzfoni ,  Avi Revivo ,  Leon Portman ,  Ronit Ephrat ,  Oren Pereg ,  Ronen Laperdon ,  Dori Shapira ,  Moshe Wasserblat

IPC分类号： G10L15/04 ,  G06F15/00

CPC分类号： G10L15/26 ,  G10L2015/088

摘要： A method and apparatus for providing real-time assistance related to an interaction associated with a contact center, comprising steps or components for: receiving at least a part of an audio signal of an interaction captured by a capturing device associated with an organization, and metadata information associated with the interaction; performing audio analysis of the at least part of the audio signal, while the interaction is still in progress to obtain audio information; categorizing at least a part of the metadata information and the audio information, to determine a category associated with the interaction, while the interaction is still in progress to obtain audio information; and taking an action associated with the category.

摘要翻译： 一种用于提供与与联络中心相关联的交互的实时协助的方法和装置，包括步骤或组件，用于：接收由与组织相关联的捕获设备捕获的交互的音频信号的至少一部分，以及元数据 与交互相关的信息; 执行音频信号的至少部分的音频分析，同时交互作用仍在进行中以获得音频信息; 对所述元数据信息和所述音频信息的至少一部分进行分类，以确定与所述交互相关联的类别，同时所述交互仍在进行中以获得音频信息; 并采取与该类别相关的行动。

公开(公告)号：US08145482B2

公开(公告)日：2012-03-27

申请号：US12126884

申请日：2008-05-25

申请人： Ezra Daya ,  Oren Pereg ,  Yuval Lubowich ,  Moshe Wasserblat

发明人： Ezra Daya ,  Oren Pereg ,  Yuval Lubowich ,  Moshe Wasserblat

IPC分类号： G10L15/06 ,  G10L15/18

CPC分类号： G10L15/063 ,  G10L15/18 ,  G10L2015/088 ,  G10L2015/226

摘要： Methods and apparatus for the enhancement of speech to text engines, by providing indications to the correctness of the found words, based on additional sources besides the internal indication provided by the STT engine. The enhanced indications comprise sources of data such as acoustic features, CTI features, phonetic search and others. The apparatus and methods also enable the detection of important or significant keywords found in audio files, thus enabling more efficient usages, such as further processing or transfer of interactions to relevant agents, escalation of issues, or the like. The methods and apparatus employ a training phase in which word model and key phrase model are generated for determining an enhanced correctness indication for a word and an enhanced importance indication for a key phrase, based on the additional features.

摘要翻译： 除了STT引擎提供的内部指示之外，还可以通过提供对发现的词语的正确性的指示来增强语言到文本引擎的方法和装置。 增强的指示包括诸如声学特征，CTI特征，语音搜索等的数据源。 该装置和方法还能够检测在音频文件中发现的重要或重要的关键词，从而实现更有效的用途，例如进一步处理或转移相关代理人的交互，升级问题等。 所述方法和装置采用训练阶段，其中基于附加特征，生成词模型和密钥短语模型，用于确定词的增强正确性指示和关键短语的增强重要性指示。