专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明授权

US06208971B1 Method and apparatus for command recognition using data-driven semantic inference 有权
标题翻译：使用数据驱动语义推理的命令识别方法和装置
公开(公告)号：US06208971B1
公开(公告)日：2001-03-27
申请号：US09183070
申请日：1998-10-30
申请人： Jerome R. Bellegarda , Kim E. A. Silverman
发明人： Jerome R. Bellegarda , Kim E. A. Silverman
IPC分类号： G10L1522
CPC分类号： G10L15/1822 , G10L15/22 , G10L2015/223
摘要： A method and apparatus for command recognition using data-driven semantic inference includes recognizing a sequence of words received as the voice command. Data-driven semantic inference is then used with the recognized sequence of words to recognize the voice command. Thus, the command is identified on the basis of the semantics of words of the spoken command rather than the particular grammar of each of predetermined different ways the command could be worded.
摘要翻译：使用数据驱动语义推理的用于命令识别的方法和装置包括识别作为语音命令接收的单词序列。然后使用数据驱动的语义推断与识别的单词序列来识别语音命令。因此，该命令是基于口头命令的单词的语义来识别的，而不是命令可以被用来指定的各种预定的不同方式的特定语法。

62. 发明授权

US6154722A Method and apparatus for a speech recognition system language model that integrates a finite state grammar probability and an N-gram probability 失效
标题翻译：用于语音识别系统语言模型的方法和装置，其集成了有限状态语法概率和N-gram概率
公开(公告)号：US6154722A
公开(公告)日：2000-11-28
申请号：US993939
申请日：1997-12-18
申请人： Jerome R. Bellegarda
发明人： Jerome R. Bellegarda
IPC分类号： G10L15/18
CPC分类号： G10L15/197 , G10L15/193
摘要： A method and an apparatus for a speech recognition system that uses a language model based on an integrated finite state grammar probability and an n-gram probability are provided. According to one aspect of the invention, speech signals are received into a processor of a speech recognition system. The speech signals are processed using a speech recognition system hosting a language model. The language model is produced by integrating a finite state grammar probability and an n-gram probability. In the integration, the n-gram probability is modified based on information provided by the finite state grammar probability; thus, the finite state grammar probability is subordinate to the n-gram probability. The language model is used by a decoder along with at least one acoustic model to perform a hypothesis search on an acoustic sequence to provide a word sequence output. The word sequence generated is representative of the received speech signals.
摘要翻译：提供了一种使用基于综合有限状态语法概率和n-gram概率的语言模型的语音识别系统的方法和装置。根据本发明的一个方面，语音信号被接收到语音识别系统的处理器中。使用承载语言模型的语音识别系统处理语音信号。语言模型是通过整合有限状态语法概率和n-gram概率来产生的。在整合中，基于由有限状态语法概率提供的信息修改n-gram概率; 因此，有限状态语法概率从属于n-gram概率。语言模型由解码器以及至少一个声学模型使用以在声学序列上执行假设搜索以提供字序列输出。所产生的字序列代表所接收的语音信号。

63. 发明授权

US5839106A Large-vocabulary speech recognition using an integrated syntactic and semantic statistical language model 失效
标题翻译：使用综合句法和语义统计语言模型的大词汇语音识别
公开(公告)号：US5839106A
公开(公告)日：1998-11-17
申请号：US768122
申请日：1996-12-17
申请人： Jerome R. Bellegarda
发明人： Jerome R. Bellegarda
IPC分类号： G10L15/18 , G01L5/06 , G01L9/06
CPC分类号： G10L15/1815 , G10L15/197
摘要： Methods and apparatus for performing large-vocabulary speech recognition employing an integrated syntactic and semantic statistical language model. In an exemplary embodiment, a stochastic language model is developed using a hybrid paradigm in which latent semantic analysis is combined with, and subordinated to, a conventional n-gram paradigm. The hybrid paradigm provides an estimate of the likelihood that a particular word, chosen from an underlying vocabulary will occur given a prevailing contextual history. The estimate is computed as a conditional probability that a word will occur given an "integrated" history combining an n-word, syntactic-type history with a semantic-type history based on a much larger contextual framework. Thus, the exemplary embodiment seamlessly blends local language structures with global usage patterns to provide, in a single language model, the proficiency of a short-horizon, syntactic model with the large-span effectiveness of semantic analysis.
摘要翻译：使用综合句法和语义统计语言模型进行大词汇语音识别的方法和装置。在示例性实施例中，使用混合范式来开发随机语言模型，其中潜在语义分析与常规的n-gram模式相结合，从属于常规的n-gram模式。混合范式提供了一种从基础词汇选择的特定词汇可能发生的可能性的估计，因为具有普遍的语境历史。该估计被计算为一个条件概率，一个词将会出现，给定一个“综合”的历史，它将一个n字，句法类型的历史与基于更大的语境框架的语义类型的历史相结合。因此，示例性实施例将本地语言结构与全局使用模式无缝地融合，以在单一语言模型中提供具有语义分析的大范围有效性的短视界面句法模型的熟练程度。

64. 发明授权

US5828999A Method and system for deriving a large-span semantic language model for large-vocabulary recognition systems 失效
标题翻译：用于推导大型词汇识别系统的大范围语义语言模型的方法和系统
公开(公告)号：US5828999A
公开(公告)日：1998-10-27
申请号：US643521
申请日：1996-05-06
申请人： Jerome R. Bellegarda , Yen-Lu Chow
发明人： Jerome R. Bellegarda , Yen-Lu Chow
IPC分类号： G06K9/72 , G10L15/18 , G10L5/06
CPC分类号： G10L15/1815 , G06K9/726 , G06K2209/01
摘要： A system and method for deriving a large-span semantic language model for a large vocabulary recognition system is disclosed. The method and system maps words from a vocabulary into a vector space, where each word is represented by a vector. After the vectors are mapped to the space, the vectors are clustered into a set of clusters, where each cluster represents a semantic event. After clustering the vectors, a probability that a first word will occur given a history of prior words is computed by (i) calculating a probability that the vector representing the first word belongs to each of the clusters; (ii) calculating a probability of each cluster occurring in a history of prior words; and weighting (i) by (ii) to provide the probability.
摘要翻译：公开了一种用于导出大型词汇识别系统的大范围语义语言模型的系统和方法。该方法和系统将词汇从词汇映射到向量空间，其中每个单词由向量表示。在将向量映射到空间之后，矢量被聚集成一组集群，其中每个集群表示一个语义事件。在对矢量进行聚类之后，通过（i）计算表示第一个词的向量属于每个簇的概率来计算给定先验词的历史的第一个单词的概率; （ii）计算每个簇在先前单词的历史中发生的概率; 并通过（ii）加权（i）以提供概率。

65. 发明授权

US5621809A Computer program product for automatic recognition of a consistent message using multiple complimentary sources of information 失效
标题翻译：计算机程序产品，用于使用多个免费的信息来自动识别一致的消息
公开(公告)号：US5621809A
公开(公告)日：1997-04-15
申请号：US481150
申请日：1995-06-07
申请人： Jerome R. Bellegarda , Dimitri Kanevsky
发明人： Jerome R. Bellegarda , Dimitri Kanevsky
IPC分类号： G06K9/62 , G06K9/68 , G10L15/06 , G10L15/10 , G10L15/24 , G06K9/00 , G10L5/06
CPC分类号： G06K9/6293 , G10L15/24 , G10L15/10 , G10L2015/0635
摘要： A general approach is provided for the combined use of several sources of information in the automatic recognition of a consistent message. For each message unit (e.g., word) the total likelihood score is assumed to be the weighted sum of the likelihood scores resulting from the separate evaluation of each information source. Emphasis is placed on the estimation of weighing factors used in forming this total likelihood. This method can be applied, for example, to the decoding of a consistent message using both handwriting and speech recognition. The present invention includes three procedures which provide the optimal weighing coefficients.
摘要翻译：提供了一种通用方法，用于在一致的消息的自动识别中组合使用多种信息源。对于每个消息单元（例如，单词），总概率分数被假设为由每个信息源的单独评估得到的似然分数的加权和。强调用于形成这种总可能性的称重因子的估计。该方法例如可以应用于使用手写和语音识别两者的一致消息的解码。本发明包括提供最佳称重系数的三个步骤。

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