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. 发明申请

US20190138539A1 DYNAMIC LANGUAGE MODEL 审中-公开
公开(公告)号：US20190138539A1
公开(公告)日：2019-05-09
申请号：US16200531
申请日：2018-11-26
申请人： Google, LLC
发明人： Pedro J. Moreno Mengibar , Michael H. Cohen
IPC分类号： G06F16/338 , G06F16/33 , G10L15/00 , G06F16/21 , G06F16/29 , G10L15/14 , G10L15/26 , G10L15/197 , G10L15/24
CPC分类号： G06F16/338 , G06F16/211 , G06F16/29 , G06F16/3344 , G06F16/3346 , G10L15/005 , G10L15/14 , G10L15/197 , G10L15/24 , G10L15/26 , G10L15/265 , G10L2015/0633 , G10L2015/081 , G10L2015/228
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

2. 发明授权

US10079014B2 Name recognition system 有权
公开(公告)号：US10079014B2
公开(公告)日：2018-09-18
申请号：US15643741
申请日：2017-07-07
申请人： Apple Inc.
发明人： Devang K. Naik
IPC分类号： G10L15/00 , G10L15/04 , G10L15/26 , G10L15/06 , G10L15/18 , G10L21/00 , G10L25/00 , G06F17/27 , G06F17/21 , G10L15/187 , G10L15/30 , G10L15/02
CPC分类号： G10L15/187 , G10L15/30 , G10L2015/025 , G10L2015/0633
摘要： A speech recognition system uses, in one embodiment, an extended phonetic dictionary that is obtained by processing words in a user's set of databases, such as a user's contacts database, with a set of pronunciation guessers. The speech recognition system can use a conventional phonetic dictionary and the extended phonetic dictionary to recognize speech inputs that are user requests to use the contacts database, for example, to make a phone call, etc. The extended phonetic dictionary can be updated in response to changes in the contacts database, and the set of pronunciation guessers can include pronunciation guessers for a plurality of locales, each locale having its own pronunciation guesser.

3. 发明申请

US20170270912A1 LANGUAGE MODELING BASED ON SPOKEN AND UNSPEAKABLE CORPUSES 审中-公开
公开(公告)号：US20170270912A1
公开(公告)日：2017-09-21
申请号：US15614283
申请日：2017-06-05
申请人： Microsoft Technology Licensing, LLC
发明人： Michael Levit , Shuangyu Chang , Benoit Dumoulin
IPC分类号： G10L15/06 , G10L15/18 , G10L15/19 , G10L15/10 , G10L15/14
CPC分类号： G10L15/063 , G10L15/10 , G10L15/14 , G10L15/18 , G10L15/19 , G10L2015/0633 , G10L2015/0635
摘要： A computer system for language modeling may collect training data from one or more information sources, generate a spoken corpus containing text of transcribed speech, and generate a typed corpus containing typed text. The computer system may derive feature vectors from the spoken corpus, analyze the typed corpus to determine feature vectors representing items of typed text, and generate an unspeakable corpus by filtering the typed corpus to remove each item of typed text represented by a feature vector that is within a similarity threshold of a feature vector derived from the spoken corpus. The computer system may derive feature vectors from the unspeakable corpus and train a classifier to perform discriminative data selection for language modeling based on the feature vectors derived from the spoken corpus and the feature vectors derived from the unspeakable corpus.

4. 发明申请

US20160336008A1 Cross-Language Speech Recognition and Translation 审中-公开
标题翻译：跨语言语音识别与翻译
公开(公告)号：US20160336008A1
公开(公告)日：2016-11-17
申请号：US14714046
申请日：2015-05-15
申请人： Microsoft Technology Licensing, LLC
发明人： Arul A. Menezes , Hany M. Hassan Awadalla
IPC分类号： G10L15/187 , G10L15/06 , G06F17/28 , G10L15/19 , G06F17/27 , G10L13/08
CPC分类号： G10L15/187 , G06F17/278 , G06F17/2818 , G10L15/06 , G10L15/19 , G10L2015/0633
摘要： Technologies are described herein for cross-language speech recognition and translation. An example method of speech recognition and translation includes receiving an input utterance in a first language, the input utterance having at least one name of a named entity included therein and being pronounced in a second language, utilizing a customized language model to process at least a portion of the input utterance, and identifying the at least one name of the named entity from the input utterance utilizing a phonetic representation of the at least one name of the named entity. The phonetic representation has a pronunciation of the at least one name in the second language.
摘要翻译：这里描述了用于跨语言语音识别和翻译的技术。语音识别和翻译的示例性方法包括以第一语言接收输入话语，输入话语具有包括在其中的命名实体的至少一个名称并以第二语言发音，利用定制语言模型来处理至少一个输入话语的一部分，以及利用所述命名实体的至少一个名称的语音表示，从所述输入话语中识别所述命名实体的所述至少一个名称。语音表示具有第二语言中至少一个名称的发音。

5. 发明授权

US09477652B2 Machine learning dialect identification 有权
标题翻译：机器学习方言识别
公开(公告)号：US09477652B2
公开(公告)日：2016-10-25
申请号：US14621921
申请日：2015-02-13
申请人： Facebook, Inc.
发明人： Fei Huang
IPC分类号： G06F17/20 , G06F17/27 , G06F17/21 , G06F17/28 , G10L15/00 , G10L15/26
CPC分类号： G10L15/063 , G06F17/274 , G06F17/275 , G06F17/279 , G06F17/28 , G10L15/005 , G10L15/26 , G10L2015/0633 , G10L2015/0636
摘要： Technology is disclosed for creating and tuning classifiers for language dialects and for generating dialect-specific language modules. A computing device can receive an initial training data set as a current training data set. The selection process for the initial training data set can be achieved by receiving one or more initial content items, establishing dialect parameters of each of the initial content items, and sorting each of the initial content items into one or more dialect groups based on the established dialect parameters. The computing device can generate, based on the initial training data set, a dialect classifier configured to detect language dialects of content items to be classified. The computing device can augment the current training data set with additional training data by applying the dialect classifier to candidate content items. The computing device can then update the dialect classifier based on the augmented current training data set.
摘要翻译：公开了用于创建和调整用于语言方言的分类器和用于生成方言特定语言模块的技术。计算设备可以接收初始训练数据集作为当前训练数据集。初始训练数据集的选择过程可以通过接收一个或多个初始内容项目，建立每个初始内容项目的方言参数，并且基于所建立的内容项目将每个初始内容项目分类成一个或多个方言组来实现方言参数。计算设备可以基于初始训练数据集生成被配置为检测要分类的内容项的语言方言的方言分类器。计算设备可以通过将方言分类器应用于候选内容项来增加具有附加训练数据的当前训练数据集。然后，计算设备可以基于增强的当前训练数据集来更新方言分类器。

6. 发明授权

US09471887B2 Automatic task classification based upon machine learning 有权
标题翻译：基于机器学习的自动任务分类
公开(公告)号：US09471887B2
公开(公告)日：2016-10-18
申请号：US14871595
申请日：2015-09-30
申请人： NTT DOCOMO Inc.
发明人： Hyung Sik Shin , Ronald Sujithan , Sayandev Mukherjee , Hongfeng Yin , Yang Sun , Yoshikazu Akinaga , Pero Subasic
IPC分类号： G06N99/00 , G06F15/18 , G10L15/00 , G10L15/18 , G06F17/30 , G06F9/48 , G10L15/06
CPC分类号： G06N99/005 , G06F9/4881 , G06F15/18 , G06F17/30654 , G10L15/00 , G10L15/1822 , G10L2015/0633
摘要： A system and method is provided that processes a training database of human-generated requests in each of a plurality of task categories with a machine learning algorithm to develop a task classifier model that may be applied to subsequent user requests to determine the most likely one of the task categories for the subsequent user request.
摘要翻译：提供了一种系统和方法，其利用机器学习算法处理多个任务类别中的每一个中的人产生请求的训练数据库，以开发可应用于后续用户请求的任务分类器模型，以确定最可能的一个后续用户请求的任务类别。

7. 发明申请

US20160078861A1 Discriminative Training of Document Transcription System 有权
公开(公告)号：US20160078861A1
公开(公告)日：2016-03-17
申请号：US14942349
申请日：2015-11-16
申请人： MModal IP LLC
发明人： Lambert Mathias , Girija Yegnanarayanan , Juergen Fritsch
IPC分类号： G10L15/06 , G06F17/28 , G10L15/02 , G06F17/27
CPC分类号： G10L15/063 , G06F17/271 , G06F17/2775 , G06F17/28 , G10L15/02 , G10L15/183 , G10L15/193 , G10L15/26 , G10L2015/0631 , G10L2015/0633
摘要： A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

8. 发明授权

US09251251B2 Dynamic language model 有权
公开(公告)号：US09251251B2
公开(公告)日：2016-02-02
申请号：US14719178
申请日：2015-05-21
申请人： Google Inc.
发明人： Pedro J. Moreno Mengibar , Michael H. Cohen
IPC分类号： G10L15/26 , G10L15/00 , G06F17/30 , G10L15/197 , G10L15/14 , G10L15/22 , G10L15/08
CPC分类号： G06F17/30696 , G06F17/30241 , G06F17/30292 , G06F17/30684 , G06F17/30687 , G10L15/005 , G10L15/14 , G10L15/197 , G10L15/24 , G10L15/26 , G10L15/265 , G10L2015/0633 , G10L2015/081 , G10L2015/228
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.

9. 发明授权

US09190050B2 Discriminative training of document transcription system 有权
标题翻译：文件转录系统的歧视性培训
公开(公告)号：US09190050B2
公开(公告)日：2015-11-17
申请号：US14244053
申请日：2014-04-03
申请人： MModal IP LLC
发明人： Lambert Mathias , Girija Yegnanarayanan , Juergen Fritsch
IPC分类号： G10L15/183 , G10L15/193 , G10L15/26 , G10L15/06
CPC分类号： G10L15/063 , G06F17/271 , G06F17/2775 , G06F17/28 , G10L15/02 , G10L15/183 , G10L15/193 , G10L15/26 , G10L2015/0631 , G10L2015/0633
摘要： A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.
摘要翻译：提供用于训练用于语音识别的声学模型的系统。特别地，这样的系统可以用于基于口语音频流和口头音频流的非文字转录来执行训练。这样的系统可以识别表示具有多个口头形式的概念的非文字记录中的文本。该系统可以尝试在音频流中识别在非文字转录中产生相应文本的音频流中的实际语音形式，从而产生更准确地表示语音音频流的经修改的脚本。可以使用修改和更准确的抄本来使用辨别性训练技术训练声学模型，从而产生比使用直接基于原始非文字誊本进行训练的常规技术产生的更好的声学模型。

10. 发明授权

US09086863B2 Optimally sorting a list of elements based on their singletons 有权
标题翻译：根据单身人士优先排序元素列表
公开(公告)号：US09086863B2
公开(公告)日：2015-07-21
申请号：US13646816
申请日：2012-10-08
申请人： Continental Automotive Systems, Inc.
发明人： Guillaume Lamy
IPC分类号： G06F7/24 , G10L15/065
CPC分类号： G06F7/24 , G10L15/06 , G10L15/065 , G10L15/075 , G10L2015/0633
摘要： A method provides a non-optimized list of elements, with some of the elements having multiple terms. A table of sub-elements is generated from the elements list, with each sub-element having one term only and with a number of times a sub-element appears in the elements list being weighted in the sub-elements table. A weighted singleton histogram table is generated using a singleton dictionary, and a total popularity score of each singleton is computed from the sub-elements table. For each element from the elements list, an elements score is generated based on the total popularity score of each singleton within the element. An optimally sorted list of the elements list is generated based on the elements scores.
摘要翻译：一种方法提供了非优化的元素列表，其中一些元素具有多个项。从元素列表生成子元素表，每个子元素仅具有一个项，并且子元素出现在子元素表中加权的元素列表中的次数。使用单例字典生成加权单例直方图表，并从子元素表中计算每个单例的总人气评分。对于元素列表中的每个元素，基于元素内每个单例的总人气评分得出元素得分。基于元素分数生成元素列表的最佳排序列表。

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