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

US10991363B2 Priors adaptation for conservative training of acoustic model 有权
公开(公告)号：US10991363B2
公开(公告)日：2021-04-27
申请号：US15804305
申请日：2017-11-06
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Gakuto Kurata , Bhuvana Ramabhadran , Masayuki Suzuki
IPC分类号： G10L15/14 , G10L15/02 , G10L15/16 , G10L15/065 , G10L15/20 , G10L15/06
摘要： An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

2. 发明授权

US10923110B2 Priors adaptation for conservative training of acoustic model 有权
公开(公告)号：US10923110B2
公开(公告)日：2021-02-16
申请号：US15686808
申请日：2017-08-25
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Gakuto Kurata , Bhuvana Ramabhadran , Masayuki Suzuki
IPC分类号： G10L15/14 , G10L15/02 , G10L15/16 , G10L15/065 , G10L15/20 , G10L15/06
摘要： An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

3. 发明申请

US20200034703A1 TRAINING OF STUDENT NEURAL NETWORK WITH TEACHER NEURAL NETWORKS 审中-公开
公开(公告)号：US20200034703A1
公开(公告)日：2020-01-30
申请号：US16047526
申请日：2018-07-27
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Takashi Fukuda , Masayuki Suzuki , Osamu Ichikawa , Gakuto Kurata , Samuel Thomas , Bhuvana Ramabhadran
IPC分类号： G06N3/08 , G06N3/04 , G10L15/02 , G10L25/51
摘要： A student neural network may be trained by a computer-implemented method, including: inputting common input data to each teacher neural network among a plurality of teacher neural networks to obtain a soft label output among a plurality of soft label outputs from each teacher neural network among the plurality of teacher neural networks, and training a student neural network with the input data and the plurality of soft label outputs.

4. 发明授权

US10460723B2 Sound identification utilizing periodic indications 有权
公开(公告)号：US10460723B2
公开(公告)日：2019-10-29
申请号：US15992778
申请日：2018-05-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Takashi Fukuda , Osamu Ichikawa , Bhuvana Ramabhadran
IPC分类号： G10L15/00 , G10L15/16 , G10L15/02 , G10L15/06 , G10L25/24
摘要： A computer-implemented method is provided. The computer-implemented method is performed by a speech recognition system having at least a processor. The method includes estimating sound identification information from a neural network having periodic indications and components of a frequency spectrum of an audio signal data inputted thereto. The method further includes performing a speech recognition operation on the audio signal data to decode the audio signal data into a textual representation based on the estimated sound identification information. The neural network includes a plurality of fully-connected network layers having a first layer that includes a plurality of first nodes and a plurality of second nodes. The method further comprises training the neural network by initially isolating the periodic indications from the components of the frequency spectrum in the first layer by setting weights between the first nodes and a plurality of input nodes corresponding to the periodic indications to 0.

5. 发明申请

US20190318732A1 IMPLEMENTING A WHOLE SENTENCE RECURRENT NEURAL NETWORK LANGUAGE MODEL FOR NATURAL LANGUAGE PROCESSING 有权
公开(公告)号：US20190318732A1
公开(公告)日：2019-10-17
申请号：US15954399
申请日：2018-04-16
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Yinghui Huang , Abhinav Sethy , Kartik Audhkhasi , Bhuvana Ramabhadran
IPC分类号： G10L15/197 , G10L15/16 , G10L15/06 , G10L15/22 , G06N7/00 , G06N3/08
摘要： A whole sentence recurrent neural network (RNN) language model (LM) is provided for for estimating a probability of likelihood of each whole sentence processed by natural language processing being correct. A noise contrastive estimation sampler is applied against at least one entire sentence from a corpus of multiple sentences to generate at least one incorrect sentence. The whole sentence RNN LN is trained, using the at least one entire sentence from the corpus and the at least one incorrect sentence, to distinguish the at least one entire sentence as correct. The whole sentence recurrent neural network language model is applied to estimate the probability of likelihood of each whole sentence processed by natural language processing being correct.

6. 发明授权

US10431210B1 Implementing a whole sentence recurrent neural network language model for natural language processing 有权
公开(公告)号：US10431210B1
公开(公告)日：2019-10-01
申请号：US15954399
申请日：2018-04-16
申请人： International Business Machines Corporation
发明人： Yinghui Huang , Abhinav Sethy , Kartik Audhkhasi , Bhuvana Ramabhadran
IPC分类号： G10L15/197 , G10L15/16 , G06N3/08 , G10L15/22 , G06N7/00 , G10L15/06
摘要： A whole sentence recurrent neural network (RNN) language model (LM) is provided for for estimating a probability of likelihood of each whole sentence processed by natural language processing being correct. A noise contrastive estimation sampler is applied against at least one entire sentence from a corpus of multiple sentences to generate at least one incorrect sentence. The whole sentence RNN LN is trained, using the at least one entire sentence from the corpus and the at least one incorrect sentence, to distinguish the at least one entire sentence as correct. The whole sentence recurrent neural network language model is applied to estimate the probability of likelihood of each whole sentence processed by natural language processing being correct.

7. 发明申请

US20180277104A1 SOUND IDENTIFICATION UTILIZING PERIODIC INDICATIONS 审中-公开
公开(公告)号：US20180277104A1
公开(公告)日：2018-09-27
申请号：US15992778
申请日：2018-05-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Takashi Fukuda , Osamu Ichikawa , Bhuvana Ramabhadran
IPC分类号： G10L15/16 , G10L15/02 , G10L15/06 , G10L25/24 , G10L21/038
摘要： A computer-implemented method is provided. The computer-implemented method is performed by a speech recognition system having at least a processor. The method includes estimating sound identification information from a neural network having periodic indications and components of a frequency spectrum of an audio signal data inputted thereto. The method further includes performing a speech recognition operation on the audio signal data to decode the audio signal data into a textual representation based on the estimated sound identification information. The neural network includes a plurality of fully-connected network layers having a first layer that includes a plurality of first nodes and a plurality of second nodes. The method further comprises training the neural network by initially isolating the periodic indications from the components of the frequency spectrum in the first layer by setting weights between the first nodes and a plurality of input nodes corresponding to the periodic indications to 0.

8. 发明申请

US20170193391A1 ITERATIVE INTERPOLATION OF MAXIMUM ENTROPY MODELS 审中-公开
公开(公告)号：US20170193391A1
公开(公告)日：2017-07-06
申请号：US14985670
申请日：2015-12-31
申请人： International Business Machines Corporation
发明人： Stanley Chen , Bhuvana Ramabhadran , Ebru Arisoy-Saraclar , Abhinav Sethy
IPC分类号： G06N99/00 , G10L15/197
CPC分类号： G06N20/00 , G06F17/27 , G06N20/20 , G10L15/183
摘要： A plurality of corpora is received from one or more sources. A separate model is trained on each corpus of the plurality of corpora. The models for the plurality of corpora are merged into a joint model using parameter interpolation. The models for each corpus of the plurality of corpora are retrained separately using the joint model. A single model is created based on the retrained models.

9. 发明授权

US09542389B2 Language translation in an environment associated with a virtual application 有权
标题翻译：与虚拟应用程序相关联的环境中的语言翻译
公开(公告)号：US09542389B2
公开(公告)日：2017-01-10
申请号：US14063470
申请日：2013-10-25
申请人： International Business Machines Corporation
发明人： Dimitri Kanevsky , Clifford Alan Pickover , Bhuvana Ramabhadran , Irina Rish
IPC分类号： G06F17/28 , G06Q20/10
CPC分类号： G06F17/289 , G06Q20/102
摘要： Methods and apparatus for language translation in a computing environment associated with a virtual application are presented. For example, a method for providing language translation includes determining languages of a user and a correspondent; determining one or more sequences of translators; determining a selected sequence of selected translators from the one or more sequences of the translators; requesting a change in virtual locations, within the computing environment associated with the virtual application, of one or more selected translator virtual representations of the selected translators to a virtual meeting location within the computing environment associated with the virtual application; and changing virtual locations of the one or more selected translator virtual representations to the virtual meeting location. One or more of determining languages, determining one or more sequences, determining a selected sequence, requesting a change in virtual locations, and changing virtual locations occur on a processor device.
摘要翻译：提出了与虚拟应用程序相关联的计算环境中的语言翻译的方法和装置。例如，提供语言翻译的方法包括确定用户和记者的语言; 确定翻译器的一个或多个序列; 从所述翻译器的所述一个或多个序列确定所选择的翻译器的选定序列; 在与所述虚拟应用相关联的所述计算环境内，将所选择的转换器的一个或多个所选择的转换器虚拟表示的虚拟位置改变为与所述虚拟应用相关联的所述计算环境内的虚拟会议位置; 以及将所述一个或多个所选择的翻译器虚拟表示的虚拟位置改变到所述虚拟会议位置。确定一个或多个序列，确定所选择的序列，请求虚拟位置的改变以及改变虚拟位置中的一个或多个发生在处理器设备上。

10. 发明授权

US09524734B2 Simulation 有权
标题翻译：模拟
公开(公告)号：US09524734B2
公开(公告)日：2016-12-20
申请号：US15002685
申请日：2016-01-21
申请人： International Business Machines Corporation
发明人： Sara H. Basson , Dimitri Kanevsky , Edward Emile Kelley , Bhuvana Ramabhadran
IPC分类号： G10L21/00 , G10L21/06 , G11B27/028 , G10L25/63 , G06F19/00 , G11B27/034 , G11B27/28 , H04N21/442 , G10L15/25 , G11B27/036 , G10L21/013
CPC分类号： G10L25/63 , G06F19/00 , G10L15/25 , G10L21/00 , G10L21/06 , G10L2021/0135 , G10L2021/065 , G11B27/028 , G11B27/034 , G11B27/036 , G11B27/28 , G16H50/50 , H04N21/44213
摘要： A simulation method and system. A computing system receives a first audio and/or video data stream. The first audio and/or video data stream includes data associated with a first person. The computing system monitors the first audio and/or video data stream. The computing system identifies emotional attributes comprised by the first audio and/or video data stream. The computing system generates a second audio and/or video data stream associated with the first audio and/or video data stream. The second audio and/or video data stream includes the data without the emotional attributes. The computing system stores the second audio and/or video data stream.
摘要翻译：一种模拟方法和系统。计算系统接收第一音频和/或视频数据流。第一音频和/或视频数据流包括与第一人相关联的数据。计算系统监视第一音频和/或视频数据流。计算系统识别由第一音频和/或视频数据流组成的情感属性。计算系统生成与第一音频和/或视频数据流相关联的第二音频和/或视频数据流。第二音频和/或视频数据流包括没有情感属性的数据。计算系统存储第二音频和/或视频数据流。

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