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

US5794197A Senone tree representation and evaluation 失效
标题翻译： Senone树代表和评估
公开(公告)号：US5794197A
公开(公告)日：1998-08-11
申请号：US850061
申请日：1997-05-02
申请人： Fileno A. Alleva , Xuedong Huang , Mei-Yuh Hwang
发明人： Fileno A. Alleva , Xuedong Huang , Mei-Yuh Hwang
IPC分类号： G10L15/02 , G10L15/06 , G10L15/14 , G10L15/18 , G10L5/06
CPC分类号： G10L15/146 , G10L15/187 , G10L2015/0631
摘要： A speech recognition method provides improved modeling in recognition accuracy using hidden Markov models. During training, the method creates a senone tree for each state of each phoneme encountered in a data set of training words. All output distributions received for a selected state of a selected phoneme in the set of training words are clustered together in a root node of a senone tree. Each node of the tree beginning with the root node is divided into two nodes by asking linguistic questions regarding the phonemes immediately to the left and right of a central phoneme of a triphone. At a predetermined point, the tree creation stops, resulting in leaves representing clustered output distributions known as senones. The senone trees allow all possible triphones to be mapped into a sequence of senones simply by traversing the senone trees associated with the central phoneme of the triphone. As a result, unseen triphones not encountered in the training data can be modeled with senones created using the triphones actually found in the training data.
摘要翻译：语音识别方法使用隐马尔可夫模型提供了识别精度的改进建模。在训练期间，该方法为训练词数据集中遇到的每个音素的每个状态创建一个声调树。在训练词集合中为选定音素的选定状态接收的所有输出分布被聚集在声调树的根节点中。从根节点开始的树的每个节点被分成两个节点，通过询问关于三音节的中心音素的左侧和右侧的音素的语言问题。在预定的点，树的创建停止，导致代表聚集的输出分布的叶被称为senones。声音树允许所有可能的三通电话通过遍历与三通电话的中心音素相关联的音素树来映射成一系列的单音。因此，训练数据中未见到的看不见的三重奏可以使用在训练数据中实际发现的三通奏音而创建的声音进行建模。

2. 发明授权

US06263308B1 Methods and apparatus for performing speech recognition using acoustic models which are improved through an interactive process 有权
标题翻译：使用通过交互过程改善的声学模型进行语音识别的方法和装置
公开(公告)号：US06263308B1
公开(公告)日：2001-07-17
申请号：US09531055
申请日：2000-03-20
申请人： David E. Heckerman , Fileno A. Alleva , Robert L. Rounthwaite , Daniel Rosen , Mei-Yuh Hwang , Yoram Yaacovi , John L. Manferdelli
发明人： David E. Heckerman , Fileno A. Alleva , Robert L. Rounthwaite , Daniel Rosen , Mei-Yuh Hwang , Yoram Yaacovi , John L. Manferdelli
IPC分类号： G10L1502
CPC分类号： G10L15/063
摘要： Automated methods and apparatus for synchronizing audio and text data, e.g., in the form of electronic files, representing audio and text expressions of the same work or information are described. Also described are automated methods of detecting errors and other discrepancies between the audio and text versions of the same work. A speech recognition operation is performed on the audio data initially using a speaker independent acoustic model. The recognized text in addition to audio time stamps are produced by the speech recognition operation. The recognized text is compared to the text in text data to identify correctly recognized words. The acoustic model is then retrained using the correctly recognized text and corresponding audio segments from the audio data transforming the initial acoustic model into a speaker trained acoustic model. The retrained acoustic model is then used to perform an additional speech recognition operation on the audio data. The audio and text data are synchronized using the results of the updated acoustic model. In addition, one or more error reports based on the final recognition results are generated showing discrepancies between the recognized words and the words included in the text. By retraining the acoustic model in the above described manner, improved accuracy is achieved.
摘要翻译：描述用于同步音频和文本数据的自动方法和装置，例如以电子文件的形式，表示相同作品或信息的音频和文本表达。还描述了检测相同作品的音频和文本版本之间的错误和其他差异的自动化方法。首先使用与扬声器无关的声学模型对音频数据执行语音识别操作。通过语音识别操作产生除音频时间戳之外的识别文本。将识别的文本与文本数据中的文本进行比较，以识别正确识别的字词。然后使用来自音频数据的正确识别的文本和对应的音频段将声学模型再训练，将初始声学模型变换成扬声器训练的声学模型。然后再训练的声学模型用于对音频数据执行附加的语音识别操作。使用更新的声学模型的结果来同步音频和文本数据。此外，生成基于最终识别结果的一个或多个错误报告，显示识别的单词与文本中包含的单词之间的差异。通过以上述方式重新训练声学模型，实现了提高的精度。

3. 发明授权

US6076056A Speech recognition system for recognizing continuous and isolated speech 失效
标题翻译：用于识别连续和孤立语音的语音识别系统
公开(公告)号：US6076056A
公开(公告)日：2000-06-13
申请号：US934622
申请日：1997-09-19
申请人： Xuedong D. Huang , Fileno A. Alleva , Li Jiang , Mei-Yuh Hwang
发明人： Xuedong D. Huang , Fileno A. Alleva , Li Jiang , Mei-Yuh Hwang
IPC分类号： G10L15/02 , G10L15/04 , G10L15/06 , G10L15/08 , G10L15/14 , G10L15/28
CPC分类号： G10L15/08 , G10L15/05
摘要： Speech recognition is performed by receiving isolated speech training data indicative of a plurality of discretely spoken training words, and receiving continuous speech training data indicative of a plurality of continuously spoken training words. A plurality of speech unit models is trained based on the isolated speech training data and the continuous speech training data. Speech is recognized based on the speech unit models trained.
摘要翻译：通过接收指示多个离散讲话的训练词的孤立语音训练数据，以及接收指示多个连续讲话的训练词的连续语音训练数据来执行语音识别。基于孤立语音训练数据和连续语音训练数据来训练多个语音单元模型。基于训练的语音单元模型识别语音。

4. 发明授权

US06973427B2 Method for adding phonetic descriptions to a speech recognition lexicon 失效
标题翻译：将语音描述添加到语音识别词典中的方法
公开(公告)号：US06973427B2
公开(公告)日：2005-12-06
申请号：US09748453
申请日：2000-12-26
申请人： Mei-Yuh Hwang , Fileno A. Alleva , Rebecca C. Weiss
发明人： Mei-Yuh Hwang , Fileno A. Alleva , Rebecca C. Weiss
IPC分类号： G10L15/06 , G06F17/21 , G01L15/04 , G01L15/06 , G01L15/08
CPC分类号： G10L15/063 , G10L2015/0636
摘要： A method and computer-readable medium convert the text of a word and a user's pronunciation of the word into a phonetic description to be added to a speech recognition lexicon. Initially, two possible phonetic descriptions are generated. One phonetic description is formed from the text of the word. The other phonetic description is formed by decoding a speech signal representing the user's pronunciation of the word. Both phonetic descriptions are scored based on their correspondence to the user's pronunciation. The phonetic description with the highest score is then selected for entry in the speech recognition lexicon.
摘要翻译：一种方法和计算机可读介质将单词的文本和用户的该单词的发音转换成要添加到语音识别词典的语音描述中。最初，会生成两个可能的语音描述。一个语音描述从单词的文字形成。另一个语音描述是通过对表示用户对该单词的发音的语音信号进行解码形成的。基于与用户发音的对应关系，语音描述都得分。然后选择具有最高分数的语音描述，用于语音识别词典中的输入。

5. 发明授权

US06336108B1 Speech recognition with mixtures of bayesian networks 有权
标题翻译：语音识别与贝叶斯网络的混合
公开(公告)号：US06336108B1
公开(公告)日：2002-01-01
申请号：US09220197
申请日：1998-12-23
申请人： Bo Thiesson , Christopher A. Meek , David Maxwell Chickering , David Earl Heckerman , Fileno A. Alleva , Mei-Yuh Hwang
发明人： Bo Thiesson , Christopher A. Meek , David Maxwell Chickering , David Earl Heckerman , Fileno A. Alleva , Mei-Yuh Hwang
IPC分类号： G06F1518
CPC分类号： G06K9/6296 , G06N5/025 , Y10S707/99945 , Y10S707/99948
摘要： The invention performs speech recognition using an array of mixtures of Bayesian networks. A mixture of Bayesian networks (MBN) consists of plural hypothesis-specific Bayesian networks (HSBNs) having possibly hidden and observed variables. A common external hidden variable is associated with the MBN, but is not included in any of the HSBNs. The number of HSBNs in the MBN corresponds to the number of states of the common external hidden variable, and each HSBN models the world under the hypothesis that the common external hidden variable is in a corresponding one of those states. In accordance with the invention, the MBNs encode the probabilities of observing the sets of acoustic observations given the utterance of a respective one of said parts of speech. Each of the HSBNs encodes the probabilities of observing the sets of acoustic observations given the utterance of a respective one of the parts of speech and given a hidden common variable being in a particular state. Each HSBN has nodes corresponding to the elements of the acoustic observations. These nodes store probability parameters corresponding to the probabilities with causal links representing dependencies between ones of said nodes.
摘要翻译：本发明使用贝叶斯网络混合的阵列来执行语音识别。贝叶斯网络（MBN）的混合由多个具有隐藏和观察变量的假设特定贝叶斯网络（HSBN）组成。常见的外部隐藏变量与MBN相关联，但不包括在任何HSBN中。 MBN中的HSBN的数量对应于共同外部隐藏变量的状态数，并且每个HSBN在假设下共同的外部隐藏变量处于相应的一个状态的假设下对世界进行建模。根据本发明，MBN编码了考虑到所述话音部分中的相应一个的话语来观察声学观测组的概率。每个HSBN编码观察给定语音相应的一个语音的发音并给出隐藏的公共变量处于特定状态的声学观察组的概率。每个HSBN具有对应于声学观测元素的节点。这些节点存储对应于概率的概率参数，其中因果链接表示所述节点之间的依赖关系。

6. 发明授权

US07676365B2 Method and apparatus for constructing and using syllable-like unit language models 有权
标题翻译：用于构建和使用音节类单位语言模型的方法和装置
公开(公告)号：US07676365B2
公开(公告)日：2010-03-09
申请号：US11110602
申请日：2005-04-20
申请人： Mei-Yuh Hwang , Fileno A. Alleva , Rebecca C. Weiss
发明人： Mei-Yuh Hwang , Fileno A. Alleva , Rebecca C. Weiss
IPC分类号： G10L15/06
CPC分类号： G10L15/063 , G10L2015/0636
摘要： A method and computer-readable medium use syllable-like units (SLUs) to decode a pronunciation into a phonetic description. The syllable-like units are generally larger than a single phoneme but smaller than a word. The present invention provides a means for defining these syllable-like units and for generating a language model based on these syllable-like units that can be used in the decoding process. As SLUs are longer than phonemes, they contain more acoustic contextual clues and better lexical constraints for speech recognition. Thus, the phoneme accuracy produced from SLU recognition is much better than all-phone sequence recognition.
摘要翻译：一种方法和计算机可读介质使用音节类单位（SLU）来将发音解码成语音描述。音节式单元通常大于单个音素，但小于一个单词。本发明提供了一种用于定义这些音节单元并且用于基于这些可以在解码过程中使用的音节单元来生成语言模型的装置。由于SLU比音素长，它们包含更多的声学语境线索和语音识别的更好的词汇约束。因此，从SLU识别产生的音素精度比全电话序列识别好得多。

7. 发明授权

US06694296B1 Method and apparatus for the recognition of spelled spoken words 有权
标题翻译：用于识别拼写的口语的方法和装置
公开(公告)号：US06694296B1
公开(公告)日：2004-02-17
申请号：US09706375
申请日：2000-11-03
申请人： Fileno A. Alleva , Mei-Yuh Hwang , Yun-Cheng Ju
发明人： Fileno A. Alleva , Mei-Yuh Hwang , Yun-Cheng Ju
IPC分类号： G10L1528
CPC分类号： G10L15/197 , G10L2015/086
摘要： The speech recognizer includes a dictation language model providing a dictation model output indicative of a likely word sequence recognized based on an input utterance. A spelling language model provides a spelling model output indicative of a likely letter sequence recognized based on the input utterance. An acoustic model provides an acoustic model output indicative of a likely speech unit recognized based on the input utterances. A speech recognition component is configured to access the dictation language model, the spelling language model and the acoustic model. The speech recognition component weights the dictation model output and the spelling model output in calculating likely recognized speech based on the input utterance. The speech recognizer can also be configured to confine spelled speech to an active lexicon.
摘要翻译：语音识别器包括提供语言模型输出的听写语言模型，所述听写模型输出指示基于输入语音识别的可能的单词序列。拼写语言模型提供了拼写模型输出，其指示基于输入话语识别的可能字母序列。声学模型提供指示基于输入的话语识别的可能语音单元的声学模型输出。语音识别组件被配置为访问听写语言模型，拼写语言模型和声学模型。语音识别组件基于输入的话语来计算听写模型输出和拼写模型输出，以计算可能识别的语音。语音识别器还可以被配置为将拼写的语音限制在活动词典中。

8. 发明授权

US06260011B1 Methods and apparatus for automatically synchronizing electronic audio files with electronic text files 有权
标题翻译：电子音频文件与电子文本文件自动同步的方法和装置
公开(公告)号：US06260011B1
公开(公告)日：2001-07-10
申请号：US09531054
申请日：2000-03-20
申请人： David E. Heckerman , Fileno A. Alleva , Robert L. Rounthwaite , Daniel Rosen , Mei-Yuh Hwang , Yoram Yaacovi , John L. Manferdelli
发明人： David E. Heckerman , Fileno A. Alleva , Robert L. Rounthwaite , Daniel Rosen , Mei-Yuh Hwang , Yoram Yaacovi , John L. Manferdelli
IPC分类号： G10L1508
CPC分类号： H04N21/466 , G06F17/30017 , G09B5/062 , G10L15/08 , G10L15/26 , H04N21/4307 , H04N21/435 , H04N21/4394 , H04N21/8106 , H04N21/8133
摘要： Automated methods and apparatus for synchronizing audio and text data, e.g., in the form of electronic files, representing audio and text expressions of the same work or information are described. A statistical language model is generated from the text data. A speech recognition operation is then performed on the audio data using the generated language model and a speaker independent acoustic model. Silence is modeled as a word which can be recognized. The speech recognition operation produces a time indexed set of recognized words some of which may be silence. The recognized words are globally aligned with the words in the text data. Recognized periods of silence, which correspond to expected periods of silence, and are adjoined by one or more correctly recognized words are identified as points where the text and audio files should be synchronized, e.g., by the insertion of bi-directional pointers. In one embodiment, for a text location to be identified for synchronization purposes, both words which bracket, e.g., precede and follow, the recognized silence must be correctly identified. Pointers, corresponding to identified locations of silence to be used for synchronization purposes are inserted into the text and/or audio files at the identified locations. Audio time stamps obtained from the speech recognition operation may be used as the bi-directional pointers. Synchronized text and audio data may be output in a variety of file formats.
摘要翻译：描述用于同步音频和文本数据的自动方法和装置，例如以电子文件的形式，表示相同作品或信息的音频和文本表达。从文本数据生成统计语言模型。然后使用生成的语言模型和与扬声器无关的声学模型对音频数据执行语音识别操作。沉默被模仿为可以被认可的一个词。语音识别操作产生识别字的时间索引集合，其中一些可能是静音。识别的单词与文本数据中的单词全局对齐。识别的静音期间，其对应于预期的沉默期，并且被一个或多个正确识别的字相邻，被识别为文本和音频文件应当被同步的点，例如通过插入双向指针。在一个实施例中，对于要为同步目的被识别的文本位置，必须正确地识别包括例如先前和后面的两个单词。对应于要用于同步目的的所确定的沉默位置的指针被插入到所识别位置的文本和/或音频文件中。从语音识别操作获得的音频时间戳可以用作双向指针。可以以各种文件格式输出同步的文本和音频数据。

9. 发明授权

US5710866A System and method for speech recognition using dynamically adjusted confidence measure 失效
标题翻译：使用动态调整的置信度测量语音识别的系统和方法
公开(公告)号：US5710866A
公开(公告)日：1998-01-20
申请号：US452141
申请日：1995-05-26
申请人： Fileno A. Alleva , Douglas H. Beeferman , Xuedong Huang
发明人： Fileno A. Alleva , Douglas H. Beeferman , Xuedong Huang
IPC分类号： G10L15/10 , G10L15/14 , G10L9/00
CPC分类号： G10L15/10 , G10L15/142
摘要： A computer-implemented method of recognizing an input speech utterance compares the input speech utterance to a plurality of hidden Markov models to obtain a constrained acoustic score that reflects the probability that the hidden Markov model matches the input speech utterance. The method computes a confidence measure for each hidden Markov model that reflects the probability of the constrained acoustic score being correct. The computed confidence measure is then used to adjust the constrained acoustic score. Preferably, the confidence measure is computed based on a difference between the constrained acoustic score and an unconstrained acoustic score that is computed independently of any language context. In addition, a new confidence measure preferably is computed for each input speech frame from the input speech utterance so that the constrained acoustic score is adjusted for each input speech frame.
摘要翻译：识别输入语音发音的计算机实现的方法将输入的语音话语与多个隐马尔可夫模型进行比较，以获得反映隐马尔可夫模型与输入语音话语匹配的概率的约束声学得分。该方法计算每个隐马尔可夫模型的置信度度量，该模型反映受限声学分数正确的概率。然后使用计算的置信度来调整约束的声学得分。优选地，基于约束声学得分和独立于任何语言上下文计算的无约束声学评分之间的差来计算置信度量。此外，对于每个输入语音帧，优选地根据输入语音话语计算新的置信度量度，以便针对每个输入语音帧调整约束声学得分。

10. 发明授权

US07016838B2 Method and system for frame alignment and unsupervised adaptation of acoustic models 失效
公开(公告)号：US07016838B2
公开(公告)日：2006-03-21
申请号：US10987529
申请日：2004-11-12
申请人： William H. Rockenbeck , Milind V. Mahajan , Fileno A. Alleva
发明人： William H. Rockenbeck , Milind V. Mahajan , Fileno A. Alleva
IPC分类号： G10L15/06
CPC分类号： G10L15/065
摘要： An unsupervised adaptation method and apparatus are provided that reduce the storage and time requirements associated with adaptation. Under the invention, utterances are converted into feature vectors, which are decoded to produce a transcript and alignment unit boundaries for the utterance. Individual alignment units and the feature vectors associated with those alignment units are then provided to an alignment function, which aligns the feature vectors with the states of each alignment unit. Because the alignment is performed within alignment unit boundaries, fewer feature vectors are used and the time for alignment is reduced. After alignment, the feature vector dimensions aligned to a state are added to dimension sums that are kept for that state. After all the states in an utterance have had their sums updated, the speech signal and the alignment units are deleted. Once sufficient frames of data have been received to perform adaptive training, the acoustic model is adapted.

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