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

WO2014117578A1 METHOD AND SYSTEM FOR PERFORMING AN AUDIO INFORMATION COLLECTION AND QUERY 审中-公开
标题翻译：执行音频信息收集和查询的方法和系统
公开(公告)号：WO2014117578A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/087827
申请日：2013-11-26
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： ZHANG, Xiaolong , ZHANG, Bin , LI, Deyuan , LIU, Hailong , HOU, Jie , XIE, Dadong
IPC分类号： G06F17/30
CPC分类号： G06F17/30749 , G06F17/30769
摘要： An electronic device with one or more processors, memory, and a display detects a first trigger event and, in response to detecting the first trigger event, collects a audio sample of environmental audio data associated with a media item. The device transmits information corresponding to the audio sample to a server. In response to transmitting the information, the device obtains attribute information corresponding to the audio sample, where the attribute information includes metadata for the media item, a time indicator of a position of the audio sample in the media item, and stream information for the media item. The device displays a portion of the attribute information. The device detects a second trigger event and, in response to detecting the second trigger event: determines a last obtained time indicator; streams the media item based on the stream information; and presents the media item from the last obtained time indicator.
摘要翻译：具有一个或多个处理器，存储器和显示器的电子设备检测第一触发事件，并且响应于检测到第一触发事件，收集与媒体项目相关联的环境音频数据的音频样本。设备将与音频样本相对应的信息发送到服务器。响应于发送信息，设备获取对应于音频样本的属性信息，其中属性信息包括媒体项目的元数据，媒体项目中的音频样本的位置的时间指示符，以及用于媒体的流信息项目。设备显示属性信息的一部分。该装置检测第二触发事件，并响应于检测到第二触发事件：确定最后获得的时间指示符; 基于流信息流媒体项目; 并从最后获得的时间指示器呈现媒体项目。

2. 发明申请

WO2015188629A1 METHOD AND SYSTEM FOR CLIENT-SERVER REAL-TIME INTERACTION BASED ON STREAMING MEDIA 审中-公开
标题翻译：基于流媒体的客户端服务器实时交互方法与系统
公开(公告)号：WO2015188629A1
公开(公告)日：2015-12-17
申请号：PCT/CN2015/071766
申请日：2015-01-28
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： HOU, Jie , XIE, Dadong , LIU, Hailong , CHEN, Bo
IPC分类号： H04N21/278
CPC分类号： H04L65/4084 , G06F17/30044 , G06F17/30867 , H04L65/602 , H04L67/42 , H04N21/23418 , H04N21/2387 , H04N21/42203 , H04N21/4223 , H04N21/4334 , H04N21/4758 , H04N21/6582 , H04N21/8547
摘要： A method of processing real-time streaming media is performed at a computer system having one or more processors and memory. The computer system obtains a streaming media based search request from a terminal, the search request including information from a streaming media data packet captured by the terminal. After extracting a set of streaming media features from the streaming media data packet, the computer system searches a plurality of streaming media feature sequences, each sequence corresponding to a respective streaming media source end, for a feature segment that matches the extracted set of streaming media features. After acquiring a playback timestamp of the matching feature segment and a corresponding source end identifier, the computer system searches for preconfigured interaction response information that corresponds to the acquired source end identifier and the playback timestamp and returns the corresponding interaction response information to the terminal.
摘要翻译：在具有一个或多个处理器和存储器的计算机系统上执行处理实时流媒体的方法。计算机系统从终端获得基于流媒体的搜索请求，该搜索请求包括来自终端捕获的流媒体数据包的信息。在从流媒体数据分组提取一组流媒体特征之后，计算机系统搜索与相应的流媒体源端对应的每个序列的多个流媒体特征序列，用于与提取的流媒体集合匹配的特征片段特征。在获取匹配特征段的回放时间戳和对应的源端标识符之后，计算机系统搜索与获取的源端标识符和重放时间戳相对应的预配置交互响应信息，并将相应的交互响应信息返回给终端。

3. 发明申请

WO2014117544A1 METHOD AND SYSTEM FOR RECOGNIZING SPEECH COMMANDS 审中-公开
标题翻译：用于识别语音命令的方法和系统
公开(公告)号：WO2014117544A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/085738
申请日：2013-11-21
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： YUE, Shuai , LU, Li , ZHANG, Xiang , XIE, Dadong , LIU, Haibo , CHEN, Bo , LIU, Jian
IPC分类号： G10L15/20
CPC分类号： G10L15/14 , G10L15/063 , G10L15/083 , G10L15/32 , G10L2015/088 , G10L2015/223
摘要： A method of recognizing speech commands includes generating a background acoustic model for a sound using a first sound sample, the background acoustic model characterized by a first precision metric. A foreground acoustic model is generated for the sound using a second sound sample, the foreground acoustic model characterized by a second precision metric. A third sound sample is received and decoded by assigning a weight to the third sound sample corresponding to a probability that the sound sample originated in a foreground using the foreground acoustic model and the background acoustic model. The method further includes determining if the weight meets predefined criteria for assigning the third sound sample to the foreground and, when the weight meets the predefined criteria, interpreting the third sound sample as a portion of a speech command. Otherwise, recognition of the third sound sample as a portion of a speech command is forgone.
摘要翻译：识别语音命令的方法包括使用第一声音样本产生用于声音的背景声学模型，所述背景声学模型由第一精度度量表征。使用第二声音样本为声音生成前景声学模型，前景声学模型以第二精度度量为特征。通过使用前景声学模型和背景声学模型通过对与声音样本始发于前景的概率相对应的第三声音样本分配权重来接收和解码第三声音样本。该方法还包括确定权重是否满足用于将第三声音样本分配给前景的预定准则，并且当权重满足预定标准时，将第三声音样本解释为语音命令的一部分。否则，放弃了作为语音命令的一部分的第三声音样本的识别。

4. 发明申请

WO2016004809A1 METHOD AND SYSTEM FOR TESTING AND MONITORING REAL-TIME STREAMING MEDIA RECOGNITION SERVICE PROVIDER 审中-公开
标题翻译：实时流媒体识别服务提供商的测试与监控方法与系统
公开(公告)号：WO2016004809A1
公开(公告)日：2016-01-14
申请号：PCT/CN2015/081331
申请日：2015-06-12
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： LIU, Jian , XIE, Dadong , HOU, Jie , LIU, Hailong , CHEN, Bo
IPC分类号： H04N21/24
CPC分类号： H04L41/5038 , H04L65/4076 , H04L65/607 , H04L67/42 , H04N17/004 , H04N21/24
摘要： A method of testing and monitoring a real-time streaming media recognition service provider is performed at a computer system. The computer system obtains a streaming media signal source, selects a testing sample from the streaming media signal source, records characteristics of the testing sample, and obtains an expected output according to the characteristics of the testing sample. Next, the computer system converts the testing sample into a digital streaming format preset by the service provider and initiates a media recognition request according to the testing sample in the digital streaming format to the service provider. After receiving a media recognition result of the testing sample returned by the service provider according to the media recognition request, the computer system compares the media recognition result with the expected output and indicates whether the service provider is normal in accordance with the comparison result.
摘要翻译：在计算机系统中执行测试和监视实时流媒体识别服务提供商的方法。计算机系统获取流媒体信号源，从流媒体信号源选择测试样本，记录测试样本的特征，并根据测试样本的特征获得预期输出。接下来，计算机系统将测试样本转换成由服务提供商预设的数字流格式，并根据数字流格式的测试样本向服务提供商发起媒体识别请求。在根据媒体识别请求收到服务提供商返回的测试样本的媒体识别结果之后，计算机系统将媒体识别结果与预期输出进行比较，并根据比较结果指示服务提供商是否正常。

5. 发明申请

WO2015188630A1 METHOD AND SYSTEM FOR INTERACTING WITH AUDIENCE OF MULTIMEDIA CONTENT 审中-公开
标题翻译：与多媒体内容相关的方法和系统
公开(公告)号：WO2015188630A1
公开(公告)日：2015-12-17
申请号：PCT/CN2015/071772
申请日：2015-01-28
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： LIU, Hailong , XIE, Dadong , HOU, Jie , CHEN, Bo
IPC分类号： H04N21/237 , H04N21/431 , H04N21/472 , H04N21/475 , G06F17/30
CPC分类号： H04N21/4394 , G06F17/3005 , H04L43/106 , H04L65/4076 , H04L67/02 , H04N21/23418 , H04N21/237 , H04N21/41407 , H04N21/42203 , H04N21/4223 , H04N21/44008 , H04N21/4722 , H04N21/47815 , H04N21/4782 , H04N21/812 , H04N21/8352
摘要： A method of interacting with an audience of multimedia content is disclosed. The method includes receiving, from a client device, data associated with a piece of multimedia content from a group of pieces of multimedia content that is presented to a user of the client device. The data is obtained at the client device in response to an instruction provided to the client device by the user. The method includes determining, based on the data, an identifier of the piece of multimedia content from a set of identifiers, each of which identifies a piece of multimedia content from the group of pieces of multimedia content. The method includes retrieving, based on the identifier of the piece of multimedia content, interactive content associated with the piece of multimedia content. The method includes sending the interactive content to the client device such that the client device presents the interactive content to the user.
摘要翻译：公开了一种与多媒体内容的观众交互的方法。该方法包括从客户端设备从一组多媒体内容中接收与一条多媒体内容相关联的数据，该组多媒体内容呈现给客户端设备的用户。响应于由用户提供给客户端设备的指令，在客户端设备获得数据。该方法包括基于数据确定来自一组标识符的多条多媒体内容的标识符，每个标识符标识来自多组多媒体内容的一组多媒体内容。该方法包括基于该多媒体内容的标识来检索与该片多媒体内容相关联的交互式内容。该方法包括将交互内容发送到客户端设备，使得客户端设备向用户呈现交互式内容。

6. 发明申请

WO2014117555A1 METHOD AND SYSTEM FOR AUTOMATIC SPEECH RECOGNITION 审中-公开
标题翻译：自动语音识别方法与系统
公开(公告)号：WO2014117555A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/086707
申请日：2013-11-07
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： RAO, Feng , LU, Li , CHEN, Bo , YUE, Shuai , ZHANG, Xiang , WANG, Eryu , XIE, Dadong , LI, Lou , LU, Duling
IPC分类号： G10L15/00 , G10L15/02 , G10L15/14 , G10L15/22 , G10L15/26
CPC分类号： G10L15/197
摘要： An automatic speech recognition method includes at a computer having one or more processors and a memory for storing one or more programs to be executed by the processors, obtaining a plurality of speech corpus categories through classifying and calculating raw speech corpus (801); obtaining a plurality of classified language models that respectively correspond to the plurality of speech corpus categories through language model training applied on each speech corpus category (802); obtaining an interpolation language model through implementing a weighted interpolation on each classified language model and merging the interpolated plurality of classified language models (803); constructing a decoding resource in accordance with an acoustic model and the interpolation language model (804); decoding input speech using the decoding resource, and outputting a character string with a highest probability as the recognition result of the input speech (805).
摘要翻译：自动语音识别方法包括在具有一个或多个处理器的计算机和用于存储要由处理器执行的一个或多个程序的存储器，通过分类和计算原始语音语料库（801）获得多个语音语料库类别; 通过在每个语音语料库类别（802）上应用的语言模型训练获得分别对应于多个语音语料库类别的多个分类语言模型; 通过对每个分类语言模型实施加权内插并合并内插多个分类语言模型（803）来获得内插语言模型; 根据声学模型和内插语言模型构造解码资源（804）; 使用解码资源解码输入语音，并输出具有最高概率的字符串作为输入语音的识别结果（805）。

7. 发明申请

WO2014176884A1 SYSTEMS AND METHODS FOR PROGRAM IDENTIFICATION 审中-公开
标题翻译：用于程序识别的系统和方法
公开(公告)号：WO2014176884A1
公开(公告)日：2014-11-06
申请号：PCT/CN2013/086485
申请日：2013-11-04
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： LIU, Hailong , XIE, Dadong , HOU, Jie , XIAO, Bin , LIU, Xiao , CHEN, Bo
IPC分类号： G06F17/00
CPC分类号： G06F17/30743
摘要： Systems and methods are provided for program identification. For example, a first audio fingerprint corresponding to a first audio signal is acquired; whether one or more second audio fingerprints in a predetermined fingerprint database match with the first audio fingerprint is detected, a second audio fingerprint corresponding to a second audio signal; and in response to one of the second audio fingerprints matching with the first audio fingerprint, a program associated with the matching second audio signal is provided as a result for program identification associated with the first audio signal.
摘要翻译：系统和方法被提供用于程序识别。例如，获取与第一音频信号相对应的第一音频指纹; 检测预定指纹数据库中的一个或多个第二音频指纹是否与第一音频指纹匹配，对应于第二音频信号的第二音频指纹; 并且响应于与第一音频指纹匹配的第二音频指纹之一，提供与匹配的第二音频信号相关联的节目作为与第一音频信号相关联的节目识别的结果。

8. 发明申请

WO2014176747A1 ENABLING AN INTERACTIVE PROGRAM ASSOCIATED WITH A LIVE BROADCAST ON A MOBILE DEVICE 审中-公开
标题翻译：启用与移动设备上的实时广播相关的交互式节目
公开(公告)号：WO2014176747A1
公开(公告)日：2014-11-06
申请号：PCT/CN2013/075011
申请日：2013-04-28
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： ZHANG, Xiaolong , CHEN, Pinlin , LI, Keren , LIU, Hailong , HOU, Jie , XIE, Dadong
IPC分类号： H04W4/18
CPC分类号： G06F3/04842 , G06F3/038 , G06F3/0488 , G06F17/30743 , G06F2203/0383
摘要： A method of providing an interactive content to a prospective user at a mobile device, the mobile device including a non-transitory computer readable medium including a computer executable program code and a processor for executing the computer executable program code is described. The method includes steps for initiating capture of an audio stream by shaking the mobile device; capturing the audio stream via a microphone in the mobile device; converting the captured audio stream into an audio fingerprint; sending the audio fingerprint to a server; receiving the interactive content from the server if there is a match between audio fingerprints stored on the server, and the audio fingerprint sent by the mobile device; and displaying the interactive content on the mobile device.
摘要翻译：描述了一种在移动设备处向预期用户提供交互式内容的方法，所述移动设备包括包括计算机可执行程序代码的非暂时计算机可读介质和用于执行计算机可执行程序代码的处理器。该方法包括通过摇动移动设备来开始捕获音频流的步骤; 通过移动设备中的麦克风捕获音频流; 将捕获的音频流转换成音频指纹; 将音频指纹发送到服务器; 如果服务器上存储的音频指纹与由移动设备发送的音频指纹之间存在匹配，则从服务器接收交互内容; 以及在所述移动设备上显示所述交互式内容。

9. 发明申请

WO2014117577A1 METHOD AND SYSTEM FOR AUTOMATIC SPEECH RECOGNITION 审中-公开
标题翻译：自动语音识别方法与系统
公开(公告)号：WO2014117577A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/087816
申请日：2013-11-26
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： YUE, Shuai , LU, Li , ZHANG, Xiang , XIE, Dadong , CHEN, Bo , RAO, Feng
IPC分类号： G10L15/193 , G10L15/28 , G10L15/00
CPC分类号： G10L15/193 , G10L15/083
摘要： A method and system for automatic speech recognition is provided. The method includes generating a decoding network that includes a primary sub-network and a classification sub-network. The primary sub-network includes a classification node corresponding to the classification sub-network. The classification sub-network corresponds to a group of uncommon words. Speech input is received and decoded by instantiating a token in the primary sub-network and passing the token through the primary network. When the token reaches the classification node, the method includes transferring the token to the classification sub-network and passing the token through the classification sub-network. When the token reaches an accept node of the classification sub-network, the method includes returning a result of the token passing through the classification sub-network to the primary sub-network. The result includes one or more words in the group of uncommon words. A string corresponding to the speech input is output that includes the one or more words.
摘要翻译：提供了一种自动语音识别的方法和系统。该方法包括生成包括主子网和分类子网的解码网络。主子网包括与分类子网对应的分类节点。分类子网对应于一组不常见的单词。通过在主子网中实例化令牌并传递令牌通过主网络来接收和解码语音输入。当令牌到达分类节点时，该方法包括将令牌传送到分类子网，并通过分类子网传递令牌。当令牌到达分类子网络的接受节点时，该方法包括将通过分类子网络的令牌的结果返回到主子网络。结果包括不常见词组中的一个或多个单词。输出与语音输入对应的字符串，其中包含一个或多个单词。

10. 发明申请

WO2014117542A1 METHOD AND DEVICE FOR AUDIO RECOGNITION 审中-公开
标题翻译：用于音频识别的方法和装置
公开(公告)号：WO2014117542A1
公开(公告)日：2014-08-07
申请号：PCT/CN2013/085309
申请日：2013-10-16
申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED
发明人： LIU, Hailong , XIE, Dadong , HOU, Jie , XIAO, Bin , LIU, Xiao , CHEN, Bo
IPC分类号： G10L15/30
CPC分类号： G10L15/30 , G06F17/30743 , G10H1/00 , G10H5/005 , G10L25/18 , G10L25/51
摘要： A method and device for performing audio recognition, including: collecting a first audio document to be recognized; initiating calculation of first characteristic information of the first audio document, including: conducting time-frequency analysis for the first audio document to generate a first preset number of phase channels; and extracting at least one peak value characteristic point from each phase channel of the first preset number of phrase channels, where the at least one peak value characteristic point of each phase channel constitutes the peak value characteristic point sequence of said each phase channel; and obtaining a recognition result for the first audio document, wherein the recognition result is identified based on the first characteristic information, and wherein the first characteristic information is calculated based on the respective peak value characteristic point sequences of the preset number of phase channels.
摘要翻译：一种用于执行音频识别的方法和装置，包括：收集要识别的第一音频文档; 开始计算第一音频文档的第一特征信息，包括：对第一音频文档进行时间 - 频率分析以产生第一预设数量的相位通道; 以及从所述第一预设数量的短语通道的每个相位通道提取至少一个峰值特征点，其中每个相位通道的至少一个峰值特征点构成所述每个相位通道的峰值特征点序列; 并且获得第一音频文档的识别结果，其中基于第一特征信息识别识别结果，并且其中基于预设数量的相位通道的相应峰值特征点序列来计算第一特征信息。

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