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. 发明授权

US4400788A Continuous speech pattern recognizer 失效
标题翻译：连续语音识别器
公开(公告)号：US4400788A
公开(公告)日：1983-08-23
申请号：US248570
申请日：1981-03-27
申请人： Cory S. Myers , Frank C. Pirz , Lawrence R. Rabiner
发明人： Cory S. Myers , Frank C. Pirz , Lawrence R. Rabiner
IPC分类号： G10L11/00 , G10L15/00 , G10L15/10 , G10L15/12 , G10L1/00
CPC分类号： G10L15/12 , G10L15/00
摘要： This speech recognizer concatenates a string of reference isolated-words for comparison with the unknown string of connected-words. The invention includes a level-building (LB) algorithm, "level" implying a location in a sequence of words. A constrained endpoint dynamic-time-warp algorithm, in which the slope of the warping function is restricted between 1/2 and 2, is used to find the best alignment between an unknown continuous-word test pattern, and a concatenated sequence of L reference patterns. Properties of the LB algorithm include: modification of the references; back-track decision logic; heuristic selection of multiple candidates, and syntax constraints. As a result, the processing required is less than two-level dynamic-program-matching and sampling algorithms.
摘要翻译：该语音识别器连接一串参考隔离词，用于与未知字符串的连接词进行比较。本发明包括水平建立（LB）算法，“水平”意味着单词序列中的位置。使用约束的端点动态时间 - 扭曲算法，其中扭曲函数的斜率被限制在1/2和2之间，用于找到未知连续字测试模式和L参考的级联序列之间的最佳对准模式。 LB算法的属性包括：修改引用; 后轨决策逻辑; 多个候选人的启发式选择和语法约束。因此，所需的处理小于两级动态程序匹配和采样算法。

2. 发明授权

US4454586A Method and apparatus for generating speech pattern templates 失效
标题翻译：用于生成语音模式模板的方法和装置
公开(公告)号：US4454586A
公开(公告)日：1984-06-12
申请号：US322748
申请日：1981-11-19
申请人： Frank C. Pirz , Lawrence R. Rabiner , Jay G. Wilpon
发明人： Frank C. Pirz , Lawrence R. Rabiner , Jay G. Wilpon
IPC分类号： G10L11/00 , G10L15/02 , G10L15/12 , G10L1/00
CPC分类号： G10L15/12
摘要： A system for generating speech pattern templates for use with either speech recognition or speech synthesis. Reference demisyllable templates are first generated from a reference first speaker using both manual and automatic analysis. The analysis for a second speaker is simplified and automated by comparing with the first speaker's templates. The second speaker speaks the same words at a rate time-warped to match the first speakers rate and template. We define a demisyllable as each of the two halves of a syllable, assuming a syllable starts and ends with a noisy consonant, and the syllable is split at its vowel center, thereby simplifying concatenation and comparison. Key features of the invention include generating a set of signals representative of the time alignment between the first and second speaker's templates, and the time-of-occurence boundaries of each syllable in a word.
摘要翻译：一种用于产生用于语音识别或语音合成的语音模式模板的系统。首先使用手动和自动分析从参考的第一个扬声器生成参考分解模板。通过与第一个演讲人的模板进行比较，简化和自动化第二个演讲者的分析。第二个发言人以相同的时间说出一致的话，以匹配第一个演讲者的速度和模板。我们将一个分音节定义为音节的两个半部分，假设音节开始和结尾是一个嘈杂的辅音，并且音节在其元音中心分裂，从而简化了连接和比较。本发明的主要特征包括产生一组代表第一和第二说话者模板之间的时间对准的信号以及一个单词中每个音节的发生时间边界。

3. 再颁专利

USRE32012E Spoken word controlled automatic dialer 失效
标题翻译：口语字自动拨号器
公开(公告)号：USRE32012E
公开(公告)日：1985-10-22
申请号：US648691
申请日：1984-09-07
申请人： Frank C. Pirz , Lawrence R. Rabiner , Aaron E. Rosenberg , Jay G. Wilpon
发明人： Frank C. Pirz , Lawrence R. Rabiner , Aaron E. Rosenberg , Jay G. Wilpon
IPC分类号： G10L15/22 , H04M1/27
CPC分类号： G10L15/22 , H04M1/271
摘要： A speech controlled dialing circuit identifies input utterances which may be a command word (mode select), repertory word (dialing name or number), or nonrecognized ("Other"). Responsive to the identification of each occurring input utterance, a set of predetermined templates are selected to identify the next occuring utterance. A programmed microprocessor system is described to implement the main controller function.

4. 再颁专利

USRE31188E Multiple template speech recognition system 失效
标题翻译：多模板语音识别系统
公开(公告)号：USRE31188E
公开(公告)日：1983-03-22
申请号：US336067
申请日：1981-12-31
申请人： Frank C. Pirz , Lawrence R. Rabiner
发明人： Frank C. Pirz , Lawrence R. Rabiner
IPC分类号： G10L11/02 , G10L15/06
CPC分类号： G10L25/87 , G10L15/063
摘要： A speech analyzer for recognizing an unknown utterance as one of a set of reference words is adapted to generate a feature signal set for each utterance of every reference word. At least one template signal is produced for each reference word which template signal is representative of a group of feature signal sets. Responsive to a feature signal set formed from the unknown utterance and each reference word template signal, a signal representative of the similarity between the unknown utterance and the template signal is generated. A plurality of similarity signals for each reference word is selected and a signal corresponding to the average of said selected similarity signals is formed. The average similarity signals are compared to identify the unknown utterance as the most similar reference word. Features of the invention include: template formation by successive clustering involving partitioning feature signal sets into groups of predetermined similarity by centerpoint clustering, and recognition by comparing the average of selected similarity measures of a time-warped unknown feature signal set with the cluster-derived reference templates for each vocabulary word.

5. 发明授权

US4400828A Word recognizer 失效
标题翻译：字识别器
公开(公告)号：US4400828A
公开(公告)日：1983-08-23
申请号：US248547
申请日：1981-03-27
申请人： Frank C. Pirz , Lawrence R. Rabiner , Jay G. Wilpon
发明人： Frank C. Pirz , Lawrence R. Rabiner , Jay G. Wilpon
IPC分类号： G10L11/00 , G10L15/00 , G10L15/10 , G10L15/12 , G10L1/00 , G06K9/62
CPC分类号： G10L15/12 , G10L15/00
摘要： An input word is recognized as one of a set of reference words. A set of word distance signals representative of the correspondence of the input word to the reference words is generated. A set of weighted word distance signals is also generated. Responsive to the word distance signals and the weighted word distance signals, the reference word that most closely corresponds to the input word is selected.
摘要翻译：输入字被识别为一组参考词之一。产生表示输入字与参考字的对应关系的一组字距离信号。还产生一组加权字距离信号。响应于字距离信号和加权字距离信号，选择最接近输入字的参考字。

6. 发明授权

US4181821A Multiple template speech recognition system 失效
标题翻译：多模板语音识别系统
公开(公告)号：US4181821A
公开(公告)日：1980-01-01
申请号：US956438
申请日：1978-10-31
申请人： Frank C. Pirz , Lawrence R. Rabiner
发明人： Frank C. Pirz , Lawrence R. Rabiner
IPC分类号： G10L11/00 , G10L11/02 , G10L15/02 , G10L15/06 , G10L15/10 , G10L1/00
CPC分类号： G10L25/87 , G10L15/063
摘要： A speech analyzer for recognizing an unknown utterance as one of a set of reference words is adapted to generate a feature signal set for each utterance of every reference word. At least one template signal is produced for each reference word which template signal is representative of a group of feature signal sets. Responsive to a feature signal set formed from the unknown utterance and each reference word template signal, a signal representative of the similarity between the unknown utterance and the template signal is generated. A plurality of similarity signals for each reference word is selected and a signal corresponding to the average of said selected similarity signals is formed. The average similarity signals are compared to identify the unknown utterance as the most similar reference word. Features of the invention include: template formation by successive clustering involving partitioning feature signal sets into groups of predetermined similarity by centerpoint clustering, and recognition by comparing the average of selected similarity measures of a time-warped unknown feature signal set with the cluster-derived reference templates for each vocabulary word.
摘要翻译：用于将未知发音识别为一组参考词之一的语音分析器适于为每个参考词的每个发声产生一组特征信号。为每个参考字产生至少一个模板信号，该模板信号代表一组特征信号组。响应于由未知发音和每个参考字模板信号形成的特征信号组，产生表示未知发音和模板信号之间的相似性的信号。选择每个参考字的多个相似度信号，并且形成与所述选择的相似度信号的平均值对应的信号。比较平均相似度信号以将未知话语识别为最相似的参考词。本发明的特征包括：通过连续聚类的模板形成，其涉及通过中心点聚类将特征信号组划分成预定相似度的组，以及通过将时变未知特征信号集合的所选相似性度量与所述聚类导出参考的平均值进行比较来进行识别每个词汇单词的模板。

7. 发明授权

US4349700A Continuous speech recognition system 失效
标题翻译：连续语音识别系统
公开(公告)号：US4349700A
公开(公告)日：1982-09-14
申请号：US138647
申请日：1980-04-08
申请人： Frank C. Pirz , Lawrence R. Rabiner
发明人： Frank C. Pirz , Lawrence R. Rabiner
IPC分类号： G10L11/00 , G10L15/00 , G10L15/10 , G10L15/12 , G10L1/00
CPC分类号： G10L15/12 , G10L15/00
摘要： Recognition of continuous speech by comparison with prestored isolated words may be confused by the merging together of spoken adjacent words (coarticulation). Improved recognition is attained by generating overlap-words, e.g., words whose first phoneme is the end phoneme of the preceding word in a string of words. The reference candidate series of overlap-words is transformed under dynamic time warping so as to time-match the utterance series of overlap-words.
摘要翻译：通过与预先存储的孤立词相比，连续语言的识别可能会被混合在一起的口语相邻单词（coarticulation）而混淆。通过产生重叠词，例如，其第一个音素是字串中的前一个单词的结束音素的单词，可以获得改进的识别。重叠词的参考候选序列在动态时间扭曲下进行变换，以便与重叠词的话语序列进行时间匹配。

8. 发明授权

US4348550A Spoken word controlled automatic dialer 失效
标题翻译：口语字自动拨号器
公开(公告)号：US4348550A
公开(公告)日：1982-09-07
申请号：US128842
申请日：1980-06-09
申请人： Frank C. Pirz , Lawrence R. Rabiner , Aaron E. Rosenberg , Jay G. Wilpon
发明人： Frank C. Pirz , Lawrence R. Rabiner , Aaron E. Rosenberg , Jay G. Wilpon
IPC分类号： G10L15/22 , H04M1/27 , G10L1/00 , H04M1/274
CPC分类号： H04M1/271 , G10L15/22
摘要： A speech controlled dialing circuit identifies input utterances which may be a command word (mode select), repertory word (dialing name or number), or non-recognized ("Other"). Responsive to the identification of each occurring input utterance, a set of predetermined templates are selected to identify the next occuring utterance. A programmed microprocessor system is described to implement the main controller function.
摘要翻译：语音控制拨号电路识别可以是命令字（模式选择），汇总字（拨号名称或号码）或未识别（“其他”）的输入话语。响应于每个发生的输入话语的识别，选择一组预定模板以识别下一个发生的话语。描述了编程的微处理器系统来实现主控制器功能。

9. 发明授权

US5509104A Speech recognition employing key word modeling and non-key word modeling 失效
标题翻译：语音识别采用关键词建模和非关键词建模
公开(公告)号：US5509104A
公开(公告)日：1996-04-16
申请号：US132430
申请日：1993-10-06
申请人： Chin H. Lee , Lawrence R. Rabiner , Jay G. Wilpon
发明人： Chin H. Lee , Lawrence R. Rabiner , Jay G. Wilpon
IPC分类号： G10L15/00 , G10L15/14 , G10L5/00
CPC分类号： G10L15/142 , G10L2015/088
摘要： Speaker independent recognition of small vocabularies, spoken over the long distance telephone network, is achieved using two types of models, one type for defined vocabulary words (e.g., collect, calling-card, person, third-number and operator), and one type for extraneous input which ranges from non-speech sounds to groups of non-vocabulary words (e.g. `I want to make a collect call please`). For this type of key word spotting, modifications are made to a connected word speech recognition algorithm based on state-transitional (hidden Markov) models which allow it to recognize words from a pre-defined vocabulary list spoken in an unconstrained fashion. Statistical models of both the actual vocabulary words and the extraneous speech and background noises are created. A syntax-driven connected word recognition system is then used to find the best sequence of extraneous input and vocabulary word models for matching the actual input speech.
摘要翻译：使用两种类型的模型来实现对长途电话网络上的小词汇的独立识别，一种用于定义的词汇单词（例如，收集，呼叫卡，人，第三号码和运营商）的模型，以及一种类型对于从非语音声音到非词汇单词组（例如“我想要收集电话”）的无关输入。对于这种类型的关键词发现，对基于状态转换（隐马尔科夫）模型的连接词语音识别算法进行修改，这允许其识别来自以无限制方式说明的预定义词汇列表中的单词。创建实际词汇单词和无关语音和背景噪声的统计模型。然后使用语法驱动的连接词识别系统来找到用于匹配实际输入语音的外来输入和词汇词模型的最佳序列。

10. 再颁专利

USRE33597E Hidden Markov model speech recognition arrangement 失效
标题翻译：隐马尔科夫模型语音识别安排
公开(公告)号：USRE33597E
公开(公告)日：1991-05-28
申请号：US190606
申请日：1988-05-05
申请人： Stephen E. Levinson , Lawrence R. Rabiner , Man M. Sondhi
发明人： Stephen E. Levinson , Lawrence R. Rabiner , Man M. Sondhi
IPC分类号： G10L15/14
CPC分类号： G10L15/142
摘要： A speech recognizer includes a plurality of stored constrained hidden Markov model reference templates and a set of stored signals representative of prescribed acoustic features of the said plurality of reference patterns. The Markov model template includes a set of N state signals. The number of states is preselected to be independent of the reference pattern acoustic features and preferably substantially smaller than the number of acoustic feature frames of the reference patterns. An input utterance is analyzed to form a sequence of said prescribed feature signals representative of the utterance. The utterance representative prescribed feature signal sequence is combined with the N state constrained hidden Markov model template signals to form a signal representative of the probability of the utterance being each reference pattern. The input speech pattern is identified as one of the reference patterns responsive to the probability representative signals.

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