专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20080270136A1 Methods and Apparatus for Use in Speech Recognition Systems for Identifying Unknown Words and for Adding Previously Unknown Words to Vocabularies and Grammars of Speech Recognition Systems 有权
标题翻译：用于识别未知词语的语音识别系统中使用的方法和装置，以及将以前未知的词添加到语音识别系统的语义和语法
公开(公告)号：US20080270136A1
公开(公告)日：2008-10-30
申请号：US12133762
申请日：2008-06-05
申请人： Sabine Deligne , Ramesh A. Gopinath , Dimitri Kanevsky , Mahesh Viswanathan
发明人： Sabine Deligne , Ramesh A. Gopinath , Dimitri Kanevsky , Mahesh Viswanathan
IPC分类号： G10L15/18
CPC分类号： G10L15/19 , G10L15/063 , G10L15/183 , G10L2015/0631
摘要： The present invention concerns methods and apparatus for identifying and assigning meaning to words not recognized by a vocabulary or grammar of a speech recognition system. In an embodiment of the invention, the word may be in an acoustic vocabulary of the speech recognition system, but may be unrecognized by an embedded grammar of a language model of the speech recognition system. In another embodiment of the invention, the word may not be recognized by any vocabulary associated with the speech recognition system. In embodiments of the invention, at least one hypothesis is generated for an utterance not recognized by the speech recognition system. If the at least one hypothesis meets at least one predetermined criterion, a sword or more corresponding to the at least one hypothesis is added to the vocabulary of the speech recognition system. In other embodiments of the invention, before adding the word to the vocabulary of the speech recognition system, the at least one hypothesis may be presented to the user of the speech recognition system to determine if that is what the used intended when the user spoke.
摘要翻译：本发明涉及用于识别和分配对语音识别系统的词汇或语法不被识别的词语的含义的方法和装置。在本发明的一个实施例中，该词可以在语音识别系统的声学词汇中，但是可能由语音识别系统的语言模型的嵌入语法无法识别。在本发明的另一个实施例中，该词可能不被与语音识别系统相关联的任何词汇识别。在本发明的实施例中，为语音识别系统未识别的话语生成至少一个假设。如果所述至少一个假设满足至少一个预定标准，则将与所述至少一个假设相对应的剑或更多的剑添加到所述语音识别系统的词汇表。在本发明的其他实施例中，在将单词添加到语音识别系统的词汇表之前，可以将该至少一个假设呈现给语音识别系统的用户，以确定当用户说话时所使用的意图是什么。

12. 发明申请

US20080059180A1 MULTI-CHANNEL CODEBOOK DEPENDENT COMPENSATION 有权
标题翻译：多渠道代码依赖性补偿
公开(公告)号：US20080059180A1
公开(公告)日：2008-03-06
申请号：US11930822
申请日：2007-10-31
申请人： Sabine Deligne , Ramesh Gopinath
发明人： Sabine Deligne , Ramesh Gopinath
IPC分类号： G10L15/00
CPC分类号： G10L15/20 , G10L25/24 , G10L2021/02163
摘要： Methods and apparatus, in the context of speech recognition, for compensating in the cepstral domain for the effect of an interfering signal by using a reference signal.
摘要翻译：在语音识别的上下文中的方法和装置，用于通过使用参考信号在干扰信号的影响下在倒频域中进行补偿。

13. 发明申请

US20090030692A1 Natural Language System and Method Based on Unisolated Performance Metric 有权
标题翻译：自然语言系统与方法基于非隔离性能指标
公开(公告)号：US20090030692A1
公开(公告)日：2009-01-29
申请号：US12121329
申请日：2008-05-15
申请人： Sabine Deligne , Yuqing Gao , Vaibhava Goel , Hong-Kwang Kuo , Cheng Wu
发明人： Sabine Deligne , Yuqing Gao , Vaibhava Goel , Hong-Kwang Kuo , Cheng Wu
IPC分类号： G10L15/18
CPC分类号： G10L15/18 , G10L15/065
摘要： A natural language business system and method is developed to understand the underlying meaning of a person's speech, such as during a transaction with the business system. The system includes a speech recognition engine, and action classification engine, and a control module. The control module causes the system to execute an inventive method wherein the speech recognition and action classification models may be recursively optimized on an unisolated performance metric that is pertinent to the overall performance of the natural language business system, as opposed to the isolated model-specific criteria previously employed
摘要翻译：开发一种自然语言业务系统和方法，以了解一个人的言论的基本含义，例如在与业务系统的交易期间。该系统包括语音识别引擎，动作分类引擎和控制模块。控制模块使得系统执行本发明的方法，其中语音识别和动作分类模型可以针对与自然语言业务系统的整体性能相关的非隔离性能度量递归优化，而不是孤立的模型特定以前使用的标准

14. 发明申请

US20080059181A1 AUDIO-VISUAL CODEBOOK DEPENDENT CEPSTRAL NORMALIZATION 有权
标题翻译：视听代码依赖于CEPSTRAL正常化
公开(公告)号：US20080059181A1
公开(公告)日：2008-03-06
申请号：US11932996
申请日：2007-10-31
申请人： Sabine Deligne , Chalapathy Neti , Gerasimos Potamianos
发明人： Sabine Deligne , Chalapathy Neti , Gerasimos Potamianos
IPC分类号： G10L15/00
CPC分类号： G10L15/20 , G10L15/24
摘要： An arrangement for yielding enhanced audio features towards the provision of enhanced audio-visual features for speech recognition. Input is provided in the form of noisy audio-visual features and noisy audio features related to the noisy audio-visual features.
摘要翻译：用于产生增强的音频特征以提供用于语音识别的增强的视听特征的装置。输入以嘈杂的视听功能和与嘈杂的视听功能相关的嘈杂音频功能的形式提供。

15. 发明授权

US07319955B2 Audio-visual codebook dependent cepstral normalization 有权
标题翻译：视听码本依赖倒谱归一化
公开(公告)号：US07319955B2
公开(公告)日：2008-01-15
申请号：US10307164
申请日：2002-11-29
申请人： Sabine Deligne , Chalapathy V. Neti , Gerasimos Potamianos
发明人： Sabine Deligne , Chalapathy V. Neti , Gerasimos Potamianos
IPC分类号： G10L15/00
CPC分类号： G10L15/20 , G10L15/24
摘要： An arrangement for yielding enhanced audio features towards the provision of enhanced audio-visual features for speech recognition. Input is provided in the form of noisy audio-visual features and noisy audio features related to the noisy audio-visual features.
摘要翻译：用于产生增强的音频特征以提供用于语音识别的增强的视听特征的装置。输入以嘈杂的视听功能和与嘈杂的视听功能相关的嘈杂音频功能的形式提供。

16. 发明授权

US06314399B1 Apparatus for generating a statistical sequence model called class bi-multigram model with bigram dependencies assumed between adjacent sequences 有权
标题翻译：用于生成统计序列模型的装置，所述统计序列模型称为具有在相邻序列之间假设的二叉素依赖性的二进制多模型模型
公开(公告)号：US06314399B1
公开(公告)日：2001-11-06
申请号：US09290584
申请日：1999-04-13
申请人： Sabine Deligne , Yoshinori Sagisaka , Hideharu Nakajima
发明人： Sabine Deligne , Yoshinori Sagisaka , Hideharu Nakajima
IPC分类号： G10L1508
CPC分类号： G10L15/197 , G10L15/183
摘要： An apparatus generates a statistical class sequence model called A class bi-multigram model from input training strings of discrete-valued units, where bigram dependencies are assumed between adjacent variable length sequences of maximum length N units, and where class labels are assigned to the sequences. The number of times all sequences of units occur are counted, as well as the number of times all pairs of sequences of units co-occur in the input training strings. An initial bigram probability distribution of all the pairs of sequences is computed as the number of times the two sequences co-occur, divided by the number of times the first sequence occurs in the input training string. Then, the input sequences are classified into a pre-specified desired number of classes. Further, an estimate of the bigram probability distribution of the sequences is calculated by using an EM algorithm to maximize the likelihood of the input training string computed with the input probability distributions. The above processes are then iteratively performed to generate statistical class sequence model.
摘要翻译：一种装置从离散值单位的输入训练串中产生称为A类双二进制模型的统计类序列模型，其中假定在最大长度N个单位的相邻可变长度序列之间存在二元组依赖性，并且其中类别标签被分配给序列。对所有单元序列出现的次数进行计数，以及所有对的序列序列在输入训练序列中共同出现的次数。将所有对序列的初始二进制概率分布计算为两个序列共同发生的次数除以第一序列在输入训练序列中发生的次数。然后，输入序列被分类为预定的期望数量的类。此外，通过使用EM算法来计算序列的二进制概率分布的估计，以最大化用输入概率分布计算的输入训练序列的可能性。然后迭代地执行上述过程以产生统计类序列模型。

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