专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2009063445A2 A METHOD AND APPARATUS FOR FAST SEARCH IN CALL-CENTER MONITORING 审中-公开
标题翻译：用于快速搜索呼叫中心监控的方法和设备
公开(公告)号：WO2009063445A2
公开(公告)日：2009-05-22
申请号：PCT/IL2007/001500
申请日：2007-12-05
申请人： NICE SYSTEMS LTD. , WASSERBLAT, Moshe , EILAM, Barak , LUBOWICH, Yuval , NISSAN, Maor , LAPERDON, Ronen
发明人： WASSERBLAT, Moshe , EILAM, Barak , LUBOWICH, Yuval , NISSAN, Maor , LAPERDON, Ronen
IPC分类号： G10L15/00
CPC分类号： G06F17/30778 , G06F17/30746 , G10L15/187 , G10L15/26
摘要： A method and apparatus for indexing one or more audio signals using a speech to text engine and a phoneme detection engine, and generating a combined lattice comprising a text part and a phoneme part. A word to be searched is searched for in the text part, and if not found, or is found with low certainty is divided into phonemes and searched for in the phoneme parts of the lattice.
摘要翻译：一种用于使用语音到文本引擎和音素检测引擎来索引一个或多个音频信号的方法和装置，以及生成包括文本部分和音素部分的组合格点。在文本部分搜索要搜索的单词，如果没有找到，或者发现低确定性被分为音素并在格子的音素部分中搜索。

2. 发明申请

WO2008075329A3 METHOD AND SYSTEM FOR AUTOMATIC QUALITY EVALUATION 审中-公开
标题翻译：自动质量评估方法与系统
公开(公告)号：WO2008075329A3
公开(公告)日：2009-04-09
申请号：PCT/IL2006001474
申请日：2006-12-21
申请人： NICE SYSTEMS LTD , IDAN YIZHAK , WASSERBLAT MOSHE , HASSIDI OFFER
发明人： IDAN YIZHAK , WASSERBLAT MOSHE , HASSIDI OFFER
IPC分类号： H04M3/00
CPC分类号： H04M3/5175
摘要： A method and apparatus for automatic quality evaluation of an activity related to an organization, such as an agent of an organization which intereacts with a calling party, a product, a campaign or the like, based on any combination of one or more of the following: the interaction itself and particularly its vocal part; meta data related to the call, to the call parties or to the environment; information extracted from the call or general information (Fig. 1). The method may be activated off-line or on-line, in which case an alert can be generated (Fig. 1, alert generation 138) for one or more calls.
摘要翻译：一种用于对与组织有关的活动进行自动质量评估的方法和装置，所述组织例如与主叫方，产品，运动等相互联系的组织的代理，基于以下一个或多个的任何组合：互动本身，特别是其声乐部分; 与呼叫相关的元数据，呼叫方或环境; 从呼叫或一般信息中提取的信息（图1）。该方法可以离线或在线激活，在这种情况下，可以为一个或多个呼叫生成警报（图1，警报生成138）。

3. 发明申请

WO2008096336A3 METHOD AND SYSTEM FOR LAUGHTER DETECTION 审中-公开
公开(公告)号：WO2008096336A3
公开(公告)日：2008-08-14
申请号：PCT/IL2007/000180
申请日：2007-02-08
申请人： NICE SYSTEMS LTD. , PEREG, Oren , WASSERBLAT, Moshe
发明人： PEREG, Oren , WASSERBLAT, Moshe
IPC分类号： G10L11/06 , G10L15/00 , G10L11/00
摘要： A method and apparatus for laughter detection. Laughter is detected through the presence of a sequence of at least a predetermined number such as three consecutive bursts, each burst comprising a voiced portion and an unvoiced portion. After detecting bursts, n-tuples such as triplets are detected, and a likelihood of each burst N-tuple to represent laughter is provided by comparison to predetermined thresholds. Finally, a total score is assigned to the signal based on the grades associated with the triplets and parameters such as the distance between the N-tuples, the total score representing the probability that the audio signal comprises a laughter episode. The method and apparatus preferably comprise a training step and module for determining the thresholds according to manually marked audio signals.

4. 发明申请

WO2008047339A2 METHOD AND APPARATUS FOR LARGE POPULATION SPEAKER IDENTIFICATION IN TELEPHONE INTERACTIONS 审中-公开
标题翻译：电话交互中大规模人口发言人识别的方法与装置
公开(公告)号：WO2008047339A2
公开(公告)日：2008-04-24
申请号：PCT/IL2006/001224
申请日：2006-10-25
申请人： Nice Systems Ltd. , ZIGEL, Yaniv , WASSERBLAT, Moshe
发明人： ZIGEL, Yaniv , WASSERBLAT, Moshe
IPC分类号： G10L15/02
CPC分类号： G10L17/06
摘要： A method and apparatus for determining whether a speaker uttering an utterance belongs to a predetermined set comprising known speakers, wherein a training utterance is available for each known speaker. The method and apparatus test whether features extracted from the tested utterance provide a score exceeding a threshold when matched against one or more of models constructed upon voice samples of each known speaker. The method and system further provide optional enhancements such as determining, using, and updating model normalization parameters, a fast scoring algorithm, summed calls handling, or quality evaluation for the tested utterance.
摘要翻译：一种用于确定发出话语的扬声器是否属于包括已知扬声器的预定组的方法和装置，其中训练话语可用于每个已知的说话者。该方法和装置测试当与每个已知说话者的语音样本构建的模型中的一个或多个模型匹配时，是否从测试话语中提取的特征提供超过阈值的分数。该方法和系统还提供可选的增强，例如确定，使用和更新模型归一化参数，快速评分算法，求和呼叫处理或测试话语的质量评估。

5. 发明申请

WO2009063445A3 A METHOD AND APPARATUS FOR FAST SEARCH IN CALL-CENTER MONITORING 审中-公开
标题翻译：在呼叫中心监控中快速搜索的方法和设备
公开(公告)号：WO2009063445A3
公开(公告)日：2009-08-27
申请号：PCT/IL2007001500
申请日：2007-12-05
申请人： NICE SYSTEMS LTD , WASSERBLAT MOSHE , EILAM BARAK , LUBOWICH YUVAL , NISSAN MAOR , LAPERDON RONEN
发明人： WASSERBLAT MOSHE , EILAM BARAK , LUBOWICH YUVAL , NISSAN MAOR , LAPERDON RONEN
IPC分类号： G10L15/06 , G10L15/00
CPC分类号： G06F17/30778 , G06F17/30746 , G10L15/187 , G10L15/26
摘要： A method and apparatus for indexing one or more audio signals using a speech to text engine and a phoneme detection engine, and generating a combined lattice comprising a text part and a phoneme part. A word to be searched is searched for in the text part, and if not found, or is found with low certainty is divided into phonemes and searched for in the phoneme parts of the lattice.
摘要翻译：一种用于使用语音到文本引擎和音素检测引擎来索引一个或多个音频信号并且生成包括文本部分和音素部分的组合格子的方法和装置。在文本部分中搜索要搜索的单词，并且如果未找到或者以低确定性搜索到的单词被分成音素并且在格子的音素部分中搜索。

6. 发明申请

WO2007122604A3 AUTOMATIC SPEECH ANALYSIS 审中-公开
标题翻译：自动语音分析
公开(公告)号：WO2007122604A3
公开(公告)日：2009-04-09
申请号：PCT/IL2007000179
申请日：2007-02-08
申请人： NICE SYSTEMS LTD , WASSERBLAT MOSHE , EILAM BARAK
发明人： WASSERBLAT MOSHE , EILAM BARAK
IPC分类号： G06F17/20 , G06F15/00 , G10L11/00
CPC分类号： G10L15/14 , G10L15/07
摘要： A system for providing automatic quality management regarding a level of conformity to a specific accent, including, a recording system, a statistical model database with statistical models representing speech data of different levels of conformity to a specific accent, a speech analysis system, a quality management system. Wherein the recording system is adapted to record one or more samples of a speakers speech and provide it to the speech analysis system for analysis, and wherein the speech analysis system is adapted to provide a score of the speakers speech samples to the quality management system by analyzing the recorded speech samples relative to the statistical models in the statistical model database.
摘要翻译：一种用于提供关于与特定口音一致性的水平的自动质量管理的系统，包括记录系统，统计模型数据库，其具有表示与特定重音不一致的语音数据的统计模型，语音分析系统，质量管理系统。其中记录系统适于记录扬声器语音的一个或多个样本并将其提供给语音分析系统用于分析，并且其中语音分析系统适于通过以下方式向扬声器语音样本提供评分：质量管理系统分析相对于统计模型数据库中统计模型的记录语音样本。

7. 发明申请

WO2008096336A2 METHOD AND SYSTEM FOR LAUGHTER DETECTION 审中-公开
标题翻译：检测方法和系统
公开(公告)号：WO2008096336A2
公开(公告)日：2008-08-14
申请号：PCT/IL2007000180
申请日：2007-02-08
申请人： NICE SYSTEMS LTD , PEREG OREN , WASSERBLAT MOSHE
发明人： PEREG OREN , WASSERBLAT MOSHE
IPC分类号： G10L15/02 , G10L17/00 , G10L17/26 , G10L25/78 , G10L25/93
CPC分类号： G10L17/26 , G10L25/78 , G10L25/93
摘要： A method and apparatus for laughter detection. Laughter is detected through the presence of a sequence of at least a predetermined number such as three consecutive bursts, each burst comprising a voiced portion and an unvoiced portion. After detecting bursts, n-tuples such as triplets are detected, and a likelihood of each burst N-tuple to represent laughter is provided by comparison to predetermined thresholds. Finally, a total score is assigned to the signal based on the grades associated with the triplets and parameters such as the distance between the N-tuples, the total score representing the probability that the audio signal comprises a laughter episode. The method and apparatus preferably comprise a training step and module for determining the thresholds according to manually marked audio signals.
摘要翻译：一种用于笑声检测的方法和装置。通过存在至少预定数量的序列（例如三个连续脉冲串）来检测笑声，每个脉冲串包括有声部分和无声部分。在检测到突发之后，检测诸如三元组的n元组，并且通过与预定阈值进行比较来提供每个突发N元组表示笑声的可能性。最后，基于与三元组相关联的等级和诸如N元组之间的距离的参数将总分数分配给信号，总分表示音频信号包括笑声情节的概率。该方法和装置优选地包括用于根据手动标记的音频信号来确定阈值的训练步骤和模块。

8. 发明申请

WO2017052817A1 DYNAMIC ADAPTATION OF LANGUAGE MODELS AND SEMANTIC TRACKING FOR AUTOMATIC SPEECH RECOGNITION 审中-公开
标题翻译：语言模型的动态适应和自动语音识别的语义跟踪
公开(公告)号：WO2017052817A1
公开(公告)日：2017-03-30
申请号：PCT/US2016/046162
申请日：2016-08-09
申请人： INTEL CORPORATION , WASSERBLAT, Moshe , PEREG, Oren , ASSAYAG, Michel , SIVAK, Alexander , TAITE, Shahar , RIDER, Tomer
发明人： WASSERBLAT, Moshe , PEREG, Oren , ASSAYAG, Michel , SIVAK, Alexander , TAITE, Shahar , RIDER, Tomer
IPC分类号： G10L15/14 , G10L15/30 , G10L15/183
CPC分类号： G10L15/1815 , G10L15/063 , G10L15/10 , G10L15/14 , G10L15/183 , G10L15/32 , G10L2015/0631 , G10L2015/085
摘要： Generally, this disclosure provides systems, devices, methods and computer readable media for adaptation of language models and semantic tracking to improve automatic speech recognition (ASR). A system for recognizing phrases of speech from a conversation may include an ASR circuit configured to transcribe a user's speech to a first estimated text sequence, based on a generalized language model. The system may also include a language model matching circuit configured to analyze the first estimated text sequence to determine a context and to select a personalized language model (PLM), from a plurality of PLMs, based on that context. The ASR circuit may further be configured to re-transcribe the speech based on the selected PLM to generate a lattice of paths of estimated text sequences, wherein each of the paths of estimated text sequences comprise one or more words and an acoustic score associated with each of the words.
摘要翻译：通常，本公开提供用于适应语言模型和语义跟踪以提高自动语音识别（ASR）的系统，设备，方法和计算机可读介质。用于从会话识别语音短语的系统可以包括基于广义语言模型的被配置为将用户的语音转录为第一估计文本序列的ASR电路。该系统还可以包括语言模型匹配电路，该语言模型匹配电路被配置为基于该上下文从多个PLM分析第一估计文本序列以确定上下文并选择个性化语言模型（PLM）。 ASR电路还可以被配置为基于所选择的PLM重新转录语音，以生成估计文本序列的路径的格子，其中估计文本序列的每个路径包括一个或多个单词和与每个的话。

9. 发明申请

WO2008047339A3 METHOD AND APPARATUS FOR LARGE POPULATION SPEAKER IDENTIFICATION IN TELEPHONE INTERACTIONS 审中-公开
标题翻译：电话交互中大规模人口发言人识别的方法和装置
公开(公告)号：WO2008047339A3
公开(公告)日：2011-05-19
申请号：PCT/IL2006001224
申请日：2006-10-25
申请人： NICE SYSTEMS LTD , ZIGEL YANIV , WASSERBLAT MOSHE
发明人： ZIGEL YANIV , WASSERBLAT MOSHE
IPC分类号： G10L17/00
CPC分类号： G10L17/06
摘要： A method and apparatus for determining whether a speaker uttering an utterance belongs to a predetermined set comprising known speakers, wherein a training utterance is available for each known speaker. The method and apparatus test whether features extracted from the tested utterance provide a score exceeding a threshold when matched against one or more of models constructed upon voice samples of each known speaker. The method and system further provide optional enhancements such as determining, using, and updating model normalization parameters, a fast scoring algorithm, summed calls handling, or quality evaluation for the tested utterance.
摘要翻译：一种用于确定发出话语的扬声器是否属于包括已知扬声器的预定组的方法和装置，其中训练话语可用于每个已知的说话者。该方法和装置测试当与每个已知说话者的语音样本构建的模型中的一个或多个模型匹配时，从测试话语中提取的特征是否提供超过阈值的分数。该方法和系统进一步提供可选的增强，例如确定，使用和更新模型归一化参数，快速评分算法，求和呼叫处理或测试话语的质量评估。

10. 发明申请

WO2008075329A2 METHOD AND SYSTEM FOR AUTOMATIC QUALITY EVALUATION 审中-公开
标题翻译：自动质量评估方法与系统
公开(公告)号：WO2008075329A2
公开(公告)日：2008-06-26
申请号：PCT/IL2006/001474
申请日：2006-12-21
申请人： NICE SYSTEMS LTD. , IDAN, Yizhak , WASSERBLAT, Moshe , HASSIDI, Offer
发明人： IDAN, Yizhak , WASSERBLAT, Moshe , HASSIDI, Offer
IPC分类号： H04M3/22
CPC分类号： H04M3/5175
摘要： A method and apparatus for automatic quality evaluation of an activity related to an organization, such as an agent of an organization which interacts with a calling party, a product, a campaign or the like, based on any combination of one or more of the following: the interaction itself and particularly its vocal part; meta data related to the call, to the call parties or to the environment; information extracted from the call or general information. The method may be activated off-line or on-line, in which case an alert can be generated for one or more calls.
摘要翻译：一种用于自动质量评估与组织有关的活动的方法和装置，所述活动例如与主叫方，产品，运动等相互作用的组织的代理，基于以下一个或多个的任何组合：互动本身，特别是其声乐部分; 与呼叫相关的元数据，呼叫方或环境; 从呼叫或一般信息中提取的信息。该方法可以离线或在线激活，在这种情况下，可以为一个或多个呼叫生成警报。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式