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

US11817098B1 Bias detection in speech recognition models 有权
公开(公告)号：US11817098B1
公开(公告)日：2023-11-14
申请号：US18178169
申请日：2023-03-03
申请人： Wells Fargo Bank, N.A.
发明人： Yong Yi Bay , Menglin Cao , Yang Yang
IPC分类号： G10L15/22 , G10L15/07 , G10L15/26
CPC分类号： G10L15/22 , G10L15/075 , G10L15/26 , G10L2015/226
摘要： Systems and methods for detecting demographic bias in automatic speech recognition (ASR) systems. Corpuses of transcriptions from different demographic groups are analyzed, where one of the groups is known to be susceptible to bias and another group is known not to be susceptible to bias. A difference between the transcription accuracy for the first group and a transcription accuracy for a second group is measured. ASR accuracy for each group is measured and compared to each other using both statistics-based and practicality-based methodologies to determine whether a given ASR system or model exhibits a meaningful level of bias. Based on the statistical significance and the practical significance, an alert including a recommendation to adjust the ASR model is generated.

2. 发明授权

US10839162B2 Service management control platform 有权
公开(公告)号：US10839162B2
公开(公告)日：2020-11-17
申请号：US16112067
申请日：2018-08-24
申请人： ROYAL BANK OF CANADA
发明人： Ryan Matthews , Hoda Zare
IPC分类号： G06F17/27 , G10L15/06 , G06F40/30 , G06Q10/06 , G06F40/284 , G06N20/00 , G06N7/00 , G10L15/07
CPC分类号： G06F40/30 , G06F40/284 , G06N7/005 , G06N20/00 , G06Q10/0635 , G10L15/075
摘要： A control platform that involves a natural language engine with a risk-based corpora, a rules engine with feature vectors from labelled change records, and topic model to generate an expected label for an additional change record based on training data generated from the labelled change records and the risk-based corpora.

3. 发明申请

US20190198013A1 PERSONALIZATION OF CONVERSATIONAL AGENTS THROUGH MACRO RECORDING 审中-公开
公开(公告)号：US20190198013A1
公开(公告)日：2019-06-27
申请号：US15849849
申请日：2017-12-21
申请人： International Business Machines Corporation
发明人： Martin Hirzel , Louis Mandel , Avraham E. Shinnar , Jerome Simeon , Mandana Vaziri
IPC分类号： G10L15/07 , G10L15/22 , G10L15/18 , G10L15/187
CPC分类号： G10L15/075 , G06F17/279 , G06F17/2795 , G06F17/289 , G10L15/1815 , G10L15/187 , G10L15/22 , G10L2015/223 , H04L51/02
摘要： A computer-implemented conversational agent engages in a natural language conversation with a user, interpreting the natural language conversation by parsing and tokenizing utterances in the natural language conversation. Based on interpreting, a set of utterances in the natural language conversation to be recorded as a macro is determined. The macro is stored in a database with an associated macro identifier. Replaying of the macro executes a function specified in the set of utterances.

4. 发明申请

US20180211664A1 SYSTEM AND CONVERSATION INFORMATION OUTPUT METHOD 审中-公开
公开(公告)号：US20180211664A1
公开(公告)日：2018-07-26
申请号：US15861798
申请日：2018-01-04
申请人： HITACHI, LTD.
发明人： Takashi NUMATA , Toshinori Miyoshi , Hiroki Sato
IPC分类号： G10L15/22 , G10L15/07 , G10L17/26 , G10L15/26
CPC分类号： G10L15/22 , G06F3/167 , G10L15/075 , G10L15/265 , G10L17/26 , G10L2015/227
摘要： There is provided a system in which empowerment is performed by outputting conversation information to the user, the system including: a computer including a processor, a memory, and an interface; and a measuring device that measures signals of a plurality of types, wherein the processor calculates values of conversation parameters of a plurality of attributes for evaluating a state of a user who performs the empowerment on the basis of a plurality of signals measured by the measuring device, the processor selects a selection parameter which is a conversation parameter of a change target on the basis of the values of the conversation parameters of the plurality of attributes, the processor decides conversation information for changing a value of the selection parameter, and the processor outputs the decided conversation information to the user.

5. 发明申请

US20170345416A1 System and Method for Machine-Mediated Human-Human Conversation 审中-公开
公开(公告)号：US20170345416A1
公开(公告)日：2017-11-30
申请号：US15681644
申请日：2017-08-21
申请人： Nuance Communications, Inc.
发明人： Srinivas BANGALORE
IPC分类号： G10L15/07 , G10L15/197 , G10L15/18 , G10L15/25 , G10L15/20 , G10L17/22 , G10L25/84 , G10L15/22
CPC分类号： G10L17/22 , G10L15/075 , G10L15/1822 , G10L15/197 , G10L15/20 , G10L15/25 , G10L25/84 , G10L2015/223 , G10L2015/228
摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing speech. A system configured to practice the method monitors user utterances to generate a conversation context. Then the system receives a current user utterance independent of non-natural language input intended to trigger speech processing. The system compares the current user utterance to the conversation context to generate a context similarity score, and if the context similarity score is above a threshold, incorporates the current user utterance into the conversation context. If the context similarity score is below the threshold, the system discards the current user utterance. The system can compare the current user utterance to the conversation context based on an n-gram distribution, a perplexity score, and a perplexity threshold. Alternately, the system can use a task model to compare the current user utterance to the conversation context.

6. 发明申请

US20170162191A1 PRIORITIZED CONTENT LOADING FOR VEHICLE AUTOMATIC SPEECH RECOGNITION SYSTEMS 审中-公开
公开(公告)号：US20170162191A1
公开(公告)日：2017-06-08
申请号：US14957335
申请日：2015-12-02
申请人： GM Global Technology Operations LLC
发明人： Timothy J. GROST , Ute WINTER , Matthew M. HIGHSTROM , Cody R. HANSEN
IPC分类号： G10L15/07 , G10L15/19 , G10L15/22
CPC分类号： G10L15/075 , G10L15/19 , G10L15/22 , G10L15/285 , G10L2015/223
摘要： A method of loading content items for accessibility by a vehicle automatic speech recognition (ASR) system. The method tracks content items requested by one or more users and prioritizes the loading of requested content items and/or selectively loads requested content items at least partially based on the interaction history of one or more users. The method may also adapt the ASR system based on the interaction history of one or more users to make preferred content items readily accessible instead of randomly accessible.

7. 发明授权

US09336773B2 System and method for standardized speech recognition infrastructure 有权
公开(公告)号：US09336773B2
公开(公告)日：2016-05-10
申请号：US14701535
申请日：2015-05-01
申请人： Interactions LLC
发明人： Andrej Ljolje , Bernard S. Renger , Steven Neil Tischer
IPC分类号： G10L15/06 , G10L15/07 , G10L15/08
CPC分类号： G10L15/075 , G10L15/063 , G10L15/065 , G10L15/07 , G10L15/08
摘要： Disclosed herein are systems, methods, and computer-readable storage media for selecting a speech recognition model in a standardized speech recognition infrastructure. The system receives speech from a user, and if a user-specific supervised speech model associated with the user is available, retrieves the supervised speech model. If the user-specific supervised speech model is unavailable and if an unsupervised speech model is available, the system retrieves the unsupervised speech model. If the user-specific supervised speech model and the unsupervised speech model are unavailable, the system retrieves a generic speech model associated with the user. Next the system recognizes the received speech from the user with the retrieved model. In one embodiment, the system trains a speech recognition model in a standardized speech recognition infrastructure. In another embodiment, the system handshakes with a remote application in a standardized speech recognition infrastructure.

8. 发明申请

US20160093296A1 SYSTEM AND METHOD FOR MACHINE-MEDIATED HUMAN-HUMAN CONVERSATION 有权
公开(公告)号：US20160093296A1
公开(公告)日：2016-03-31
申请号：US14963479
申请日：2015-12-09
申请人： AT&T Intellectual Property I, L.P.
发明人： Srinivas BANGALORE
IPC分类号： G10L15/07 , G10L15/25 , G10L15/20 , G10L15/197
CPC分类号： G10L15/075 , G10L15/1822 , G10L15/197 , G10L15/20 , G10L15/25 , G10L17/22 , G10L25/84 , G10L2015/223 , G10L2015/228
摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for processing speech. A system configured to practice the method monitors user utterances to generate a conversation context. Then the system receives a current user utterance independent of non-natural language input intended to trigger speech processing. The system compares the current user utterance to the conversation context to generate a context similarity score, and if the context similarity score is above a threshold, incorporates the current user utterance into the conversation context. If the context similarity score is below the threshold, the system discards the current user utterance. The system can compare the current user utterance to the conversation context based on an n-gram distribution, a perplexity score, and a perplexity threshold. Alternately, the system can use a task model to compare the current user utterance to the conversation context.

9. 发明申请

US20160012819A1 Server-Side ASR Adaptation to Speaker, Device and Noise Condition via Non-ASR Audio Transmission 有权
标题翻译：通过非ASR音频传输，服务器端ASR适应扬声器，设备和噪声条件
公开(公告)号：US20160012819A1
公开(公告)日：2016-01-14
申请号：US14770371
申请日：2013-02-28
申请人： NUANCE COMMUNICATIONS, INC.
发明人： Daniel Willett , Jean-Guy E. Dahan , William F. Ganong, III , Jianxiong Wu
IPC分类号： G10L15/07 , G06F3/16 , G10L15/22 , G10L25/84 , G10L15/18 , G10L15/14
CPC分类号： G10L15/075 , G06F3/167 , G10L15/07 , G10L15/14 , G10L15/1815 , G10L15/20 , G10L15/22 , G10L15/30 , G10L25/84 , G10L2015/223 , G10L2015/226
摘要： A mobile device is adapted for automatic speech recognition (ASR). A user interface for interaction with a user includes an input microphone for obtaining speech inputs from the user for automatic speech recognition, and an output interface for system output to the user based on ASR results that correspond to the speech input. A local controller obtains a sample of non-ASR audio from the input microphone for ASR-adaptation to channel-specific ASR characteristics, and then provides a representation of the non-ASR audio to a remote ASR server for server-side adaptation to the channel-specific ASR characteristics, and then provides a representation of an unknown ASR speech input from the input microphone to the remote ASR server for determining ASR results corresponding to the unknown ASR speech input, and then provides the system output to the output interface.
摘要翻译：移动设备适用于自动语音识别（ASR）。用于与用户交互的用户界面包括用于从用户获得用于自动语音识别的语音输入的输入麦克风，以及用于基于对应于语音输入的ASR结果向用户输出系统的输出接口。本地控制器从输入麦克风获取非ASR音频的样本，用于ASR适应信道特定ASR特性，然后向远程ASR服务器提供非ASR音频的表示，用于服务器端适配信道特定的ASR特性，然后提供从输入麦克风到远程ASR服务器的未知ASR语音输入的表示，以确定与未知ASR语音输入相对应的ASR结果，然后将系统输出提供给输出接口。

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