-
公开(公告)号:US20080312921A1
公开(公告)日:2008-12-18
申请号:US12195123
申请日:2008-08-20
申请人: Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Rameah A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
发明人: Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Rameah A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
CPC分类号: G10L15/063 , G10L15/02 , G10L15/14 , G10L2015/085
摘要: In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.
摘要翻译: 在语音识别系统中,提供了具有多个语音特征的对数线性模型的组合来识别未知语音语音。 语音识别系统使用对数线性模型对与语音识别相关的语言单位的后验概率进行建模。 后验模型捕获了语言单位给出观察到的语音特征和后验模型参数的概率。 可以使用给定多个语音特征的单词序列假设的概率来确定后验模型。 对数线性模型与来自稀疏或不完整数据的特征一起使用。 所使用的语音特征可以包括异步,重叠和统计上非独立的语音特征。 培训中使用的并非所有功能都需要出现在测试/识别中。
-
公开(公告)号:US07464031B2
公开(公告)日:2008-12-09
申请号:US10724536
申请日:2003-11-28
申请人: Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Ramesh A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
发明人: Scott E. Axelrod , Sreeram Viswanath Balakrishnan , Stanley F. Chen , Yuging Gao , Ramesh A. Gopinath , Hong-Kwang Kuo , Benoit Maison , David Nahamoo , Michael Alan Picheny , George A. Saon , Geoffrey G. Zweig
CPC分类号: G10L15/063 , G10L15/02 , G10L15/14 , G10L2015/085
摘要: In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.
摘要翻译: 在语音识别系统中,提供了具有多个语音特征的对数线性模型的组合来识别未知语音语音。 语音识别系统使用对数线性模型对与语音识别相关的语言单位的后验概率进行建模。 后验模型捕获了语言单位给出观察到的语音特征和后验模型参数的概率。 可以使用给定多个语音特征的单词序列假设的概率来确定后验模型。 对数线性模型与来自稀疏或不完整数据的特征一起使用。 所使用的语音特征可以包括异步,重叠和统计上非独立的语音特征。 培训中使用的并非所有功能都需要出现在测试/识别中。
-
公开(公告)号:US09367526B1
公开(公告)日:2016-06-14
申请号:US13190891
申请日:2011-07-26
申请人: Paul Vozila , Maximilian Bisani , Yi Su , Stephen M. Chu , Stanley F. Chen , Ruhi Sarikaya , Bhuvana Ramabhadran
发明人: Paul Vozila , Maximilian Bisani , Yi Su , Stephen M. Chu , Stanley F. Chen , Ruhi Sarikaya , Bhuvana Ramabhadran
CPC分类号: G06F17/218 , G06F17/2775 , G06F17/2785 , G06F17/30663 , G06F17/30684 , G06F17/30687 , G06F17/30705 , G06F17/30707 , G06Q10/107
摘要: A language processing application employs a classing function optimized for the underlying production application context for which it is expected to process speech. A combination of class based and word based features generates a classing function optimized for a particular production application, meaning that a language model employing the classing function uses word classes having a high likelihood of accurately predicting word sequences encountered by a language model invoked by the production application. The classing function optimizes word classes by aligning the objective of word classing with the underlying language processing task to be performed by the production application. The classing function is optimized to correspond to usage in the production application context using class-based and word-based features by computing a likelihood of a word in an n-gram and a frequency of a word within a class of the n-gram.
摘要翻译: 语言处理应用程序使用针对其预期处理语音的底层生产应用程序环境进行优化的分类功能。 基于类和基于字的特征的组合产生针对特定生产应用优化的分类功能,这意味着采用分类函数的语言模型使用具有准确预测由生产调用的语言模型遇到的单词序列的高似然性的单词类 应用。 分类函数通过将单词分类的目标与生产应用程序执行的底层语言处理任务进行对齐来优化单词类。 通过计算n-gram中的单词和n-gram类中的单词的可能性,使用基于类和基于单词的特征来优化分类功能以对应于生产应用上下文中的使用。
-
-