专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20170061970A1 Speaker Dependent Voiced Sound Pattern Detection Thresholds 审中-公开
标题翻译：扬声器相关声音模式检测阈值
公开(公告)号：US20170061970A1
公开(公告)日：2017-03-02
申请号：US14835192
申请日：2015-08-25
申请人： Malaspina Labs (Barbados), Inc.
发明人： Alexander Escott
IPC分类号： G10L17/20 , G10L17/12 , G10L15/14 , G10L17/08
CPC分类号： G10L17/20 , G10L17/04 , G10L17/08 , G10L17/12
摘要： Various implementations disclosed herein include a training module configured to determining a set of detection normalization threshold values associated with speaker dependent voiced sound pattern (VSP) detection. In some implementations, a method includes obtaining segment templates characterizing a concurrent segmentation of a first subset of a plurality of vocalization instances of a VSP, each segment template provides a stochastic characterization of how a particular portion of the VSP is vocalized by a particular speaker; generating a noisy segment matrix using a second subset of the plurality of vocalization instances of the VSP, wherein the noisy segment matrix includes one or more noisy copies of segment representations of the second subset; scoring segments from the noisy segment matrix against the segment templates; and determining detection normalization threshold values at two or more known SNR levels for at least one particular noise type based on a function of the scoring.
摘要翻译：本文公开的各种实施方案包括训练模块，其被配置为确定与与扬声器相关的有声声音模式（VSP）检测相关联的一组检测归一化阈值。在一些实现中，一种方法包括获得表征VSP的多个发声实例的第一子集的并行分割的段模板，每个段模板提供对特定扬声器的VSP的特定部分如何发声的随机表征; 使用所述VSP的所述多个发声实例的第二子集来生成噪声段矩阵，其中所述噪声段矩阵包括所述第二子集的段表示的一个或多个噪声副本; 从嘈杂片段矩阵对片段模板进行评分; 以及基于所述评分的功能，针对至少一种特定噪声类型在两个或更多个已知SNR级别确定检测归一化阈值。

72. 发明申请

US20160372121A1 Voiceprint authentication method and apparatus 审中-公开
标题翻译： Voiceprint身份验证方法和设备
公开(公告)号：US20160372121A1
公开(公告)日：2016-12-22
申请号：US14757928
申请日：2015-12-23
申请人： BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
发明人： Chao Li , Yong Guan
IPC分类号： G10L17/24 , G10L17/08 , G10L17/04 , G10L17/14
CPC分类号： G10L17/24 , G10L17/04 , G10L17/08 , G10L17/14
摘要： The present disclosure provides a voiceprint authentication method and a voiceprint authentication apparatus. The method includes: displaying a tip text to a user, the tip text being a combination of a preregistered phrase; obtaining a speech of the tip text read by the user; obtaining a pre-established registration model and determining a result of a voiceprint authentication according to the speech of the tip text and the pre-established registration model, if the speech of the tip text corresponds to the tip text.
摘要翻译：本公开提供一种声纹认证方法和声纹认证装置。该方法包括：向用户显示提示文本，提示文本是预注册短语的组合; 获取用户阅读的提示文本的语音; 如果提示文本的语音对应于提示文本，则根据提示文本的语音和预先建立的注册模型，获得预先建立的注册模型并确定声纹认证的结果。

73. 发明授权

US09514753B2 Speaker identification using hash-based indexing 有权
标题翻译：扬声器识别使用基于散列的索引
公开(公告)号：US09514753B2
公开(公告)日：2016-12-06
申请号：US14523198
申请日：2014-10-24
申请人： Google Inc.
发明人： Matthew Sharifi , Ignacio Lopez Moreno , Ludwig Schmidt
IPC分类号： G10L17/00 , G10L17/02 , G10L17/08
CPC分类号： G10L17/02 , G10L17/005 , G10L17/08 , G10L17/18 , G10L25/51
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing speaker identification. In some implementations, an utterance vector that is derived from an utterance is obtained. Hash values are determined for the utterance vector according to multiple different hash functions. A set of speaker vectors from a plurality of hash tables is determined using the hash values, where each speaker vector was derived from one or more utterances of a respective speaker. The speaker vectors in the set are compared with the utterance vector. A speaker vector is selected based on comparing the speaker vectors in the set with the utterance vector.
摘要翻译：方法，系统和装置，包括在计算机存储介质上编码的用于执行说话人识别的计算机程序。在一些实现中，获得从话语导出的话语向量。根据多个不同的哈希函数为发声向量确定哈希值。使用散列值来确定来自多个散列表的一组扬声器向量，其中每个扬声器向量是从相应说话者的一个或多个话语导出的。将集合中的扬声器矢量与发声矢量进行比较。基于将集合中的扬声器矢量与发声矢量进行比较来选择扬声器矢量。

74. 发明申请

US20160301787A1 IDENTIFYING A CONTACT BASED ON A VOICE COMMUNICATION SESSION 有权
公开(公告)号：US20160301787A1
公开(公告)日：2016-10-13
申请号：US15189895
申请日：2016-06-22
申请人： International Business Machines Corporation
发明人： Jonathan F. Brunn , Jessica W. Forrester , Stephen C. Hess , Jeffrey R. Hoy
IPC分类号： H04M1/27 , G06F3/0482 , G06F17/30 , G10L17/08 , H04M1/57 , H04M1/2745
CPC分类号： H04M1/271 , G06F3/0482 , G06F17/30477 , G06F17/3053 , G06F17/30864 , G06F17/30979 , G06Q50/01 , G10L15/08 , G10L17/00 , G10L17/005 , G10L17/08 , H04L65/1069 , H04L67/12 , H04M1/274508 , H04M1/274533 , H04M1/575 , H04M3/42042 , H04M2201/41
摘要： Arrangements described herein include identifying a voice communication session established between a first communication device and a second communication device and, based on the voice communication session established between the first communication device and the second communication device, identifying a plurality of contacts who potentially may be the second user. A list including at least a name of each of the plurality of contacts who potentially may be the second user is presented to a first user using the first communication device.

75. 发明授权

US09336778B2 Method and system for using conversational biometrics and speaker identification/verification to filter voice streams 有权
标题翻译：使用会话生物识别和扬声器识别/验证来过滤语音流的方法和系统
公开(公告)号：US09336778B2
公开(公告)日：2016-05-10
申请号：US14301408
申请日：2014-06-11
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Peeyush Jaiswal , Naveen Narayan
IPC分类号： H04M1/64 , G10L17/00 , H04M3/42 , H04M3/51 , H04M3/493
CPC分类号： G10L17/00 , G10L17/005 , G10L17/02 , G10L17/08 , G10L17/14 , G10L21/0272 , H04M3/42221 , H04M3/4936 , H04M3/5166 , H04M3/5175 , H04M2201/41
摘要： A method and system for using conversational biometrics and speaker identification and/or verification to filter voice streams during mixed mode communication. The method includes receiving an audio stream of a communication between participants. Additionally, the method includes filtering the audio stream of the communication into separate audio streams, one for each of the participants. Each of the separate audio streams contains portions of the communication attributable to a respective participant. Furthermore, the method includes outputting the separate audio streams to a storage system.
摘要翻译：一种用于在混合模式通信期间使用对话生物识别和扬声器识别和/或验证来过滤语音流的方法和系统。该方法包括接收参与者之间的通信的音频流。此外，该方法包括将通信的音频流过滤成单独的音频流，每个参与者一个。每个单独的音频流包含归属于相应参与者的通信的部分。此外，该方法包括将单独的音频流输出到存储系统。

76. 发明申请

US20160118047A1 METHOD AND SYSTEM FOR USING CONVERSATIONAL BIOMETRICS AND SPEAKER IDENTIFICATION/VERIFICATION TO FILTER VOICE STREAMS 有权
标题翻译：使用对话生物学和语音识别/验证过滤语音流的方法和系统
公开(公告)号：US20160118047A1
公开(公告)日：2016-04-28
申请号：US14988884
申请日：2016-01-06
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Peeyush JAISWAL , Naveen NARAYAN
IPC分类号： G10L17/08 , G10L17/02 , G10L17/14
CPC分类号： G10L17/00 , G10L17/005 , G10L17/02 , G10L17/08 , G10L17/14 , G10L21/0272 , H04M3/42221 , H04M3/4936 , H04M3/5166 , H04M3/5175 , H04M2201/41
摘要： A method and system for using conversational biometrics and speaker identification and/or verification to filter voice streams during mixed mode communication. The method includes receiving an audio stream of a communication between participants. Additionally, the method includes filtering the audio stream of the communication into separate audio streams, one for each of the participants. Each of the separate audio streams contains portions of the communication attributable to a respective participant. Furthermore, the method includes outputting the separate audio streams to a storage system.
摘要翻译：一种用于在混合模式通信期间使用对话生物识别和扬声器识别和/或验证来过滤语音流的方法和系统。该方法包括接收参与者之间的通信的音频流。此外，该方法包括将通信的音频流过滤成单独的音频流，每个参与者一个。每个单独的音频流包含归属于相应参与者的通信的部分。此外，该方法包括将单独的音频流输出到存储系统。

77. 发明申请

US20160111085A1 IDENTIFYING A CONTACT BASED ON A VOICE COMMUNICATION SESSION 有权
公开(公告)号：US20160111085A1
公开(公告)日：2016-04-21
申请号：US14982666
申请日：2015-12-29
申请人： International Business Machines Corporation
发明人： Jonathan F. Brunn , Jessica W. Forrester , Stephen C. Hess , Jeffrey R. Hoy
IPC分类号： G10L15/08 , H04M3/42
CPC分类号： H04M1/271 , G06F3/0482 , G06F17/30477 , G06F17/3053 , G06F17/30864 , G06F17/30979 , G06Q50/01 , G10L15/08 , G10L17/00 , G10L17/005 , G10L17/08 , H04L65/1069 , H04L67/12 , H04M1/274508 , H04M1/274533 , H04M1/575 , H04M3/42042 , H04M2201/41
摘要： Arrangements described herein include identifying a voice communication session established between a first communication device and a second communication device and, based on the voice communication session established between the first communication device and the second communication device, identifying a plurality of contacts who potentially may be the second user. A list including at least a name of each of the plurality of contacts who potentially may be the second user is presented to a first user using the first communication device.

78. 发明申请

US20150371639A1 DYNAMIC THRESHOLD FOR SPEAKER VERIFICATION 有权
标题翻译：用于演讲者验证的动态阈值
公开(公告)号：US20150371639A1
公开(公告)日：2015-12-24
申请号：US14340720
申请日：2014-07-25
申请人： Google Inc.
发明人： Jakob Foerster , Diego Melendo Casado
IPC分类号： G10L17/22 , G06F3/16 , G10L17/00 , G10L17/02
CPC分类号： G10L17/20 , G06F3/167 , G10L17/005 , G10L17/02 , G10L17/04 , G10L17/06 , G10L17/08 , G10L17/12 , G10L17/22 , G10L17/24 , G10L25/84 , H04M3/385
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a dynamic threshold for speaker verification are disclosed. In one aspect, a method includes the actions of receiving, for each of multiple utterances of a hotword, a data set including at least a speaker verification confidence score, and environmental context data. The actions further include selecting from among the data sets, a subset of the data sets that are associated with a particular environmental context. The actions further include selecting a particular data set from among the subset of data sets based on one or more selection criteria. The actions further include selecting, as a speaker verification threshold for the particular environmental context, the speaker verification confidence score. The actions further include providing the speaker verification threshold for use in performing speaker verification of utterances that are associated with the particular environmental context.
摘要翻译：公开了用于说话人验证的动态阈值的方法，系统和装置，包括在计算机存储介质上编码的计算机程序。一方面，一种方法包括针对热词的多个话语中的每一个接收包括至少说话人验证置信度得分和环境上下文数据的数据集的动作。动作还包括从数据集中选择与特定环境上下文相关联的数据集的子集。动作还包括基于一个或多个选择标准从数据集的子集中选择特定数据集。该动作进一步包括作为特定环境背景的说话者验证阈值来选择说话者验证置信度得分。该动作进一步包括提供说话者验证阈值，以用于执行与特定环境背景相关联的话语的说话者验证。

79. 发明授权

US09190062B2 User profiling for voice input processing 有权
标题翻译：用户分析语音输入处理
公开(公告)号：US09190062B2
公开(公告)日：2015-11-17
申请号：US14196243
申请日：2014-03-04
申请人： Apple Inc.
发明人： Allen P. Haughay
IPC分类号： G10L17/00 , G10L15/00 , G10L21/00 , G10L15/22 , G10L17/08 , G06F3/16
CPC分类号： G10L17/08 , G06F3/167 , G10L15/22 , G10L17/00 , G10L2015/227
摘要： This is directed to processing voice inputs received by an electronic device. In particular, this is directed to receiving a voice input and identifying the user providing the voice input. The voice input can be processed using a subset of words from a library used to identify the words or phrases of the voice input. The particular subset can be selected such that voice inputs provided by the user are more likely to include words from the subset. The subset of the library can be selected using any suitable approach, including for example based on the user's interests and words that relate to those interests. For example, the subset can include one or more words related to media items selected by the user for storage on the electronic device, names of the user's contacts, applications or processes used by the user, or any other words relating to the user's interactions with the device.
摘要翻译：这旨在处理由电子设备接收的语音输入。特别地，这旨在接收语音输入并识别提供语音输入的用户。可以使用来自用于识别语音输入的单词或短语的库的单词的子集来处理语音输入。可以选择特定子集，使得由用户提供的语音输入更可能包括来自该子集的单词。可以使用任何合适的方法来选择图书馆的子集，包括例如基于用户兴趣和与这些兴趣相关的词语。例如，子集可以包括与用户选择的用于存储在电子设备上的媒体项相关的一个或多个词，用户的联系人的名称，用户使用的应用或过程，或与用户的交互相关的任何其它单词装置。

80. 发明授权

US09147399B1 Identification using audio signatures and additional characteristics 有权
标题翻译：识别使用音频签名和附加特征
公开(公告)号：US09147399B1
公开(公告)日：2015-09-29
申请号：US13601551
申请日：2012-08-31
申请人： Gregory M. Hart , Allan Timothy Lindsay , William F. Barton , John Daniel Thimsen
发明人： Gregory M. Hart , Allan Timothy Lindsay , William F. Barton , John Daniel Thimsen
IPC分类号： G10L17/00
CPC分类号： G10L17/08 , G10L17/22
摘要： Techniques for identifying users that issue audio commands based on signatures associated with the commands and additional characteristics associated with the commands. For instance, a device that includes a microphone may capture audio uttered by a user. The device, or another device, may then compare a signature associated with a generated audio signal to audio signatures associated with known users. For instance, the device may have access to multiple audio signatures, each of which is unique to a respective user that has previously interacted with the device or with another device. The device may then use this comparison to help identify the user that uttered the audio. In addition, however, the device may utilize a characteristic other than the audio signature. Using both the comparison of the audio signature to the previously received signatures along with the additional characteristic(s), the device may make a presumed identification of the user.
摘要翻译：用于识别基于与命令相关联的签名和与命令相关联的附加特征发布音频命令的用户的技术。例如，包括麦克风的设备可以捕获用户发出的音频。然后，设备或另一设备可以将与所生成的音频信号相关联的签名与与已知用户相关联的音频签名进行比较。例如，设备可以访问多个音频签名，每个音频签名对于先前已经与设备或与另一设备交互的相应用户是唯一的。然后，设备可以使用该比较来帮助识别发出音频的用户。然而，此外，设备可以利用除音频签名之外的特性。使用音频签名与先前接收的签名的比较以及附加特征，设备可以做出用户的推定的标识。

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