-
1.发明授权公开(公告)号：US09002490B2
公开(公告)日：2015-04-07
申请号：US13086360
申请日：2011-04-13
CPC分类号： H04L65/4015 , H04L65/1069
摘要： Methods for implementing shared experiences using mobile computing devices comprise capturing audio waves associated with a media using a built-in microphone of a mobile computing device, the mobile computing device including a processor, a memory, a display screen, a built-in battery to power the mobile computing device, and a built-in communication module to enable wireless communication. A signature is generated from the audio waves captured by the microphone. Based on the signature being recognized as a known signature, the signature and positioning information are transmitted to an audio server using the wireless communication. The positioning information identifies a specific moment in the media that a user of the mobile computing device is listening, the audio server and the mobile computing device connected to a network. Activity information is received from the audio server. The activity information is related to the media and associated with a third party server connected to the network. The user of the mobile computing device is enabled to use the activity information to interact with the third party server.
摘要翻译： 使用移动计算设备实现共享体验的方法包括使用移动计算设备的内置麦克风捕获与媒体相关联的音频波，所述移动计算设备包括处理器，存储器，显示屏，内置电池 为移动计算设备供电，以及内置通信模块，以实现无线通信。 从麦克风捕获的音频波生成签名。 基于签名被识别为已知签名，使用无线通信将签名和定位信息发送到音频服务器。 定位信息识别媒体中的特定时刻，即移动计算设备的用户正在收听，音频服务器和连接到网络的移动计算设备。 从音频服务器接收活动信息。 活动信息与媒体相关联，并与连接到网络的第三方服务器相关联。 允许移动计算设备的用户使用活动信息与第三方服务器进行交互。
-
公开(公告)号：US09646603B2
公开(公告)日：2017-05-09
申请号：US12395484
申请日：2009-02-27
CPC分类号： G10L15/02 , G10L13/08 , G10L2015/025
摘要： A method, apparatus, and system are described for a continuous speech recognition engine that includes a fine speech recognizer model, a coarse sound representation generator, and a coarse match generator. The fine speech recognizer model receives a time coded sequence of sound feature frames, applies a speech recognition process to the sound feature frames and determines at least a best guess at each recognizable word that corresponds to the sound feature frames. The coarse sound representation generator generates a coarse sound representation of the recognized word. The coarse match generator determines a likelihood of the coarse sound representation actually being the recognized word based on comparing the coarse sound representation of the recognized word to a database containing the known sound of that recognized word and assigns the likelihood as a robust confidence level parameter to that recognized word.
-
3.发明申请公开(公告)号：US20120232901A1
公开(公告)日：2012-09-13
申请号：US13479707
申请日：2012-05-24
CPC分类号： G10L15/187 , G10L15/005
摘要： A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language model (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the SLMs that are based on the set of unique phoneme patterns created for each language.
摘要翻译： 描述了包括通用音素解码器（UPD）的语言识别系统。 UPD包含一个通用音素集合，表示1）所有发音在两组或多种语言中的音素，以及2）跨语言捕获音素对应，以便计算一组独特的音素模式和概率，以便识别 最有可能在音频文件中出现的两种或多种潜在语言的UPD被训练的音频文件中。 每个统计语言模型（SLM）使用为集合中的每种语言创建的一组独特的音素模式，以区分该语言集中的口语人类语言。 运行时语言标识符模块通过利用由SLM提供的基于为每种语言创建的唯一音素模式的集合提供的语言概率来识别正在说出的特定人类语言。
-
4.发明申请公开(公告)号：US20110035219A1
公开(公告)日：2011-02-10
申请号：US12535038
申请日：2009-08-04
CPC分类号： G10L15/187 , G10L15/005
摘要： A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language models (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the one or more SLMs that are based on the set of unique phoneme patterns created for each language.
摘要翻译： 描述了包括通用音素解码器（UPD）的语言识别系统。 UPD包含一个通用音素集合，表示1）所有发音在两组或多种语言中的音素，以及2）跨语言捕获音素对应，以便计算一组独特的音素模式和概率，以便识别 最有可能在音频文件中出现的两种或多种潜在语言的UPD被训练的音频文件中。 每个统计语言模型（SLM）使用为集合中的每种语言创建的一组独特的音素模式，以区分该语言集中的口语人类语言。 运行时语言标识符模块通过利用由基于为每种语言创建的唯一音素模式的集合的一个或多个SLM提供的语言概率来识别正在说出的特定人类语言。
-
公开(公告)号：US20100324901A1
公开(公告)日：2010-12-23
申请号：US12489786
申请日：2009-06-23
IPC分类号： G10L15/06
CPC分类号： G10L15/065 , G10L15/197
摘要： Various methods and apparatus are described for a speech recognition system. In an embodiment, the statistical language model (SLM) provides probability estimates of how linguistically likely a sequence of linguistic items are to occur in that sequence based on an amount of times the sequence of linguistic items occurs in text and phrases in general use. The speech recognition decoder module requests a correction module for one or more corrected probability estimates P′(z|xy) of how likely a linguistic item z follows a given sequence of linguistic items x followed by y, where (x, y, and z) are three variable linguistic items supplied from the decoder module. The correction module is trained to linguistics of a specific domain, and is located in between the decoder module and the SLM in order to adapt the probability estimates supplied by the SLM to the specific domain when those probability estimates from the SLM significantly disagree with the linguistic probabilities in that domain.
摘要翻译： 描述了用于语音识别系统的各种方法和装置。 在一个实施例中，统计语言模型（SLM）基于语言项目序列出现在通常使用的文本和短语中的次数，提供语言序列在该序列中如何语言上可能发生的概率估计。 语音识别解码器模块向修正模块请求一个或多个校正概率估计P'（z | xy），语言项目z在给定的语言项目序列x之后跟随y，其中（x，y和z） ）是从解码器模块提供的三个可变语言项目。 校正模块被训练成特定领域的语言学，并且位于解码器模块和SLM之间，以便当来自SLM的这些概率估计显着不同于语言学的情况时，将SLM提供的概率估计适应于特定领域 该领域的概率。
-
公开(公告)号：US20100223056A1
公开(公告)日：2010-09-02
申请号：US12395484
申请日：2009-02-27
CPC分类号： G10L15/02 , G10L13/08 , G10L2015/025
摘要： A method, apparatus, and system are described for a continuous speech recognition engine that includes a fine speech recognizer model, a coarse sound representation generator, and a coarse match generator. The fine speech recognizer model receives a time coded sequence of sound feature frames, applies a speech recognition process to the sound feature frames and determines at least a best guess at each recognizable word that corresponds to the sound feature frames. The coarse sound representation generator generates a coarse sound representation of the recognized word. The coarse match generator determines a likelihood of the coarse sound representation actually being the recognized word based on comparing the coarse sound representation of the recognized word to a database containing the known sound of that recognized word and assigns the likelihood as a robust confidence level parameter to that recognized word.
摘要翻译： 对于包括精细语音识别器模型，粗略声音表示发生器和粗略匹配发生器的连续语音识别引擎，描述了一种方法，装置和系统。 精细语音识别器模型接收声音特征帧的时间编码序列，对声音特征帧应用语音识别处理，并确定对应于声音特征帧的每个可识别词的至少最佳猜测。 粗音表示发生器产生识别字的粗声表示。 粗略匹配发生器基于将识别的字的粗略声音表示与包含该识别字的已知声音的数据库进行比较，确定粗略声音表示实际上是识别的字的可能性，并将可靠性分配为鲁棒的置信水平参数 这个公认的话。
-
7.发明授权Method for spatially-accurate location of a device using audio-visual information 有权使用视听信息对设备进行空间准确定位的方法公开(公告)号：US08447329B2
公开(公告)日：2013-05-21
申请号：US13023508
申请日：2011-02-08
CPC分类号： H04W64/006 , G01S5/18 , G01S5/30 , G01S11/14 , G06F17/30247 , G06F17/30265 , G06F17/30268 , G06F17/30817 , G06K9/00671 , G06K9/00979
摘要： A system to determine positions of mobile computing devices and provide direction information includes a first mobile computing device configured to broadcast a first chirp signal, a second mobile computing device configured to broadcast a second chirp signal indicating receipt of the first chirp signal and a first time information about when the first chirp signal is received, and a third mobile computing device configured broadcast a third chirp signal indicating (a) receipt of the first and second chirp signals and (b) a second time information about when the first and second chirp signals are received. The first mobile computing device is configured to use the first and second time information to determine a position of the second mobile computing device. The first mobile computing device is also configured to transmit text messages to the second mobile computing device to direct a user of the second mobile computing device to a position of a user of the first mobile computing device.
摘要翻译： 用于确定移动计算设备的位置并提供方向信息的系统包括被配置为广播第一线性调频信号的第一移动计算设备，被配置为广播指示接收到第一线性调频脉冲信号的第二线性调频信号的第二移动计算设备，以及第一时间 关于接收到第一线性调频信号何时的信息，以及配置为广播第三线性调频脉冲信号的第三移动计算设备，其指示（a）接收到第一和第二线性调频脉冲信号，以及（b）关于第一和第二线性调频脉冲信号何时 被收到 第一移动计算设备被配置为使用第一和第二时间信息来确定第二移动计算设备的位置。 第一移动计算设备还被配置为向第二移动计算设备发送文本消息以将第二移动计算设备的用户引导到第一移动计算设备的用户的位置。
-
8.发明授权公开(公告)号：US08401840B2
公开(公告)日：2013-03-19
申请号：US13479707
申请日：2012-05-24
IPC分类号： G06F17/20
CPC分类号： G10L15/187 , G10L15/005
摘要： A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language model (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the SLMs that are based on the set of unique phoneme patterns created for each language.
摘要翻译： 描述了包括通用音素解码器（UPD）的语言识别系统。 UPD包含一个通用音素集合，表示1）所有发音在两组或多种语言中的音素，以及2）跨语言捕获音素对应，以便计算一组独特的音素模式和概率，以便识别 最有可能在音频文件中出现的两种或多种潜在语言的UPD被训练的音频文件中。 每个统计语言模型（SLM）使用为集合中的每种语言创建的一组独特的音素模式，以区分该语言集中的口语人类语言。 运行时语言标识符模块通过利用由SLM提供的基于为每种语言创建的唯一音素模式的集合提供的语言概率来识别正在说出的特定人类语言。
-
公开(公告)号：US08229743B2
公开(公告)日：2012-07-24
申请号：US12489786
申请日：2009-06-23
IPC分类号： G10L15/00
CPC分类号： G10L15/065 , G10L15/197
摘要： Various methods and apparatus are described for a speech recognition system. In an embodiment, the statistical language model (SLM) provides probability estimates of how linguistically likely a sequence of linguistic items are to occur in that sequence based on an amount of times the sequence of linguistic items occurs in text and phrases in general use. The speech recognition decoder module requests a correction module for one or more corrected probability estimates P′(z|xy) of how likely a linguistic item z follows a given sequence of linguistic items x followed by y, where (x, y, and z) are three variable linguistic items supplied from the decoder module. The correction module is trained to linguistics of a specific domain, and is located in between the decoder module and the SLM in order to adapt the probability estimates supplied by the SLM to the specific domain when those probability estimates from the SLM significantly disagree with the linguistic probabilities in that domain.
摘要翻译： 描述了用于语音识别系统的各种方法和装置。 在一个实施例中，统计语言模型（SLM）基于语言项目序列出现在通常使用的文本和短语中的次数，提供语言序列在该序列中如何语言上可能发生的概率估计。 语音识别解码器模块向修正模块请求一个或多个校正概率估计P'（z | xy），语言项目z在给定的语言项目序列x之后跟随y，其中（x，y和z） ）是从解码器模块提供的三个可变语言项目。 校正模块被训练成特定领域的语言学，并且位于解码器模块和SLM之间，以便当来自SLM的概率估计显着不同于语言学时，将SLM提供的概率估计值适应于特定领域 该领域的概率。
-
10.发明授权公开(公告)号：US08190420B2
公开(公告)日：2012-05-29
申请号：US12535038
申请日：2009-08-04
IPC分类号： G06F17/20
CPC分类号： G10L15/187 , G10L15/005
摘要： A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language models (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the one or more SLMs that are based on the set of unique phoneme patterns created for each language.
摘要翻译： 描述了包括通用音素解码器（UPD）的语言识别系统。 UPD包含一个通用音素集合，表示1）所有发音在两组或多种语言中的音素，以及2）跨语言捕获音素对应，以便计算一组独特的音素模式和概率，以便识别 最有可能在音频文件中出现的两种或多种潜在语言的UPD被训练的音频文件中。 每个统计语言模型（SLM）使用为集合中的每种语言创建的一组独特的音素模式，以区分该语言集中的口语人类语言。 运行时语言标识符模块通过利用由基于为每种语言创建的唯一音素模式的集合的一个或多个SLM提供的语言概率来识别正在说出的特定人类语言。
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.023 秒)
