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

US20110276325A1 Training A Transcription System 有权
标题翻译：培训转录系统
公开(公告)号：US20110276325A1
公开(公告)日：2011-11-10
申请号：US12774054
申请日：2010-05-05
申请人： Todd C. Tatum , Michael A. Ramalho , Paul M. Dunn , Shantanu Sarkar , Tyrone T. Thorsen , Alan D. Gatzke
发明人： Todd C. Tatum , Michael A. Ramalho , Paul M. Dunn , Shantanu Sarkar , Tyrone T. Thorsen , Alan D. Gatzke
IPC分类号： G10L15/26
CPC分类号： G10L15/07 , G10L2015/0638
摘要： According to certain embodiments, training a transcription system includes accessing recorded voice data of a user from one or more sources. The recorded voice data comprises voice samples. A transcript of the recorded voice data is accessed. The transcript comprises text representing one or more words of each voice sample. The transcript and the recorded voice data are provided to a transcription system to generate a voice profile for the user. The voice profile comprises information used to convert a voice sample to corresponding text.
摘要翻译：根据某些实施例，训练转录系统包括从一个或多个来源访问用户的记录语音数据。记录的语音数据包括语音样本。录制的语音数据的记录被访问。成绩单包括表示每个语音样本的一个或多个单词的文本。将转录本和记录的语音数据提供给转录系统以生成用户的语音简档。语音简档包括用于将语音样本转换为相应文本的信息。

2. 发明授权

US09009040B2 Training a transcription system 有权
标题翻译：训练转录系统
公开(公告)号：US09009040B2
公开(公告)日：2015-04-14
申请号：US12774054
申请日：2010-05-05
申请人： Todd C. Tatum , Michael A. Ramalho , Paul M. Dunn , Shantanu Sarkar , Tyrone T. Thorsen , Alan D. Gatzke
发明人： Todd C. Tatum , Michael A. Ramalho , Paul M. Dunn , Shantanu Sarkar , Tyrone T. Thorsen , Alan D. Gatzke
IPC分类号： G10L15/00 , G10L15/07 , G10L15/06
CPC分类号： G10L15/07 , G10L2015/0638
摘要： According to certain embodiments, training a transcription system includes accessing recorded voice data of a user from one or more sources. The recorded voice data comprises voice samples. A transcript of the recorded voice data is accessed. The transcript comprises text representing one or more words of each voice sample. The transcript and the recorded voice data are provided to a transcription system to generate a voice profile for the user. The voice profile comprises information used to convert a voice sample to corresponding text.
摘要翻译：根据某些实施例，训练转录系统包括从一个或多个来源访问用户的记录语音数据。记录的语音数据包括语音样本。录制的语音数据的记录被访问。成绩单包括表示每个语音样本的一个或多个单词的文本。将转录本和记录的语音数据提供给转录系统以生成用户的语音简档。语音简档包括用于将语音样本转换为相应文本的信息。

3. 发明授权

US08600750B2 Speaker-cluster dependent speaker recognition (speaker-type automated speech recognition) 有权
标题翻译：扬声器群集相关扬声器识别（扬声器型自动语音识别）
公开(公告)号：US08600750B2
公开(公告)日：2013-12-03
申请号：US12795959
申请日：2010-06-08
申请人： Michael A. Ramalho , Todd C. Tatum , Shantanu Sarkar
发明人： Michael A. Ramalho , Todd C. Tatum , Shantanu Sarkar
IPC分类号： G10L15/06
CPC分类号： G10L15/075 , G10L2015/0631
摘要： In an example embodiment, there is disclosed herein an automatic speech recognition (ASR) system that employs speaker clustering (or speaker type) for transcribing audio. A large corpus of audio with corresponding transcripts is analyzed to determine a plurality of speaker types (e.g., dialects). The ASR system is trained for each speaker type. Upon encountering a new user, the ASR system attempts to map the user to a speaker type. After the new user is mapped to a speaker type, the ASR employs the speaker type for transcribing audio from the new user.
摘要翻译：在示例实施例中，这里公开了一种使用用于转录音频的扬声器聚类（或扬声器类型）的自动语音识别（ASR）系统。分析具有对应的抄本的大的音频语料库以确定多个扬声器类型（例如，方言）。针对每个扬声器类型训练ASR系统。在遇到新用户时，ASR系统尝试将用户映射到扬声器类型。在新用户映射到扬声器类型之后，ASR使用扬声器类型从新用户转录音频。

4. 发明申请

US20110301949A1 SPEAKER-CLUSTER DEPENDENT SPEAKER RECOGNITION (SPEAKER-TYPE AUTOMATED SPEECH RECOGNITION) 有权
标题翻译：扬声器相关扬声器识别（扬声器型自动语音识别）
公开(公告)号：US20110301949A1
公开(公告)日：2011-12-08
申请号：US12795959
申请日：2010-06-08
申请人： Michael A. Ramalho , Todd C. Tatum , Shantanu Sarkar
发明人： Michael A. Ramalho , Todd C. Tatum , Shantanu Sarkar
IPC分类号： G10L15/00
CPC分类号： G10L15/075 , G10L2015/0631
摘要： In an example embodiment, there is disclosed herein an automatic speech recognition (ASR) system that employs speaker clustering (or speaker type) for transcribing audio. A large corpus of audio with corresponding transcripts is analyzed to determine a plurality of speaker types (e.g., dialects). The ASR system is trained for each speaker type. Upon encountering a new user, the ASR system attempts to map the user to a speaker type. After the new user is mapped to a speaker type, the ASR employs the speaker type for transcribing audio from the new user.
摘要翻译：在示例实施例中，这里公开了一种使用用于转录音频的扬声器聚类（或扬声器类型）的自动语音识别（ASR）系统。分析具有对应的抄本的大的音频语料库以确定多个扬声器类型（例如，方言）。针对每个扬声器类型训练ASR系统。在遇到新用户时，ASR系统尝试将用户映射到扬声器类型。在新用户映射到扬声器类型之后，ASR使用扬声器类型从新用户转录音频。

5. 发明申请

US20150172355A1 SYSTEM AND METHOD FOR IMPROVING AUDIO QUALITY DURING WEB CONFERENCES OVER LOW-SPEED NETWORK CONNECTIONS 审中-公开
标题翻译：在网络会议中通过低速网络连接改善音频质量的系统和方法
公开(公告)号：US20150172355A1
公开(公告)日：2015-06-18
申请号：US14576855
申请日：2014-12-19
申请人： Michael A. Ramalho , Mihailo Zilovic , Laurent Kim-Huy Pham , Gary A. Skrabutenas
发明人： Michael A. Ramalho , Mihailo Zilovic , Laurent Kim-Huy Pham , Gary A. Skrabutenas
IPC分类号： H04L29/06
CPC分类号： H04L65/80 , H04L12/1818 , H04L65/403
摘要： A method that includes; (1) transmitting, at a first transmit time point, a first probe packet over a network connection to a conferencing server immediately before transmitting a data packet, the first probe packet arriving at the conferencing server at a first receive time point; (2) transmitting, at a second transmit time point, a second probe packet over the network connection to the conferencing server immediately after transmitting the data packet, the second probe packet arriving at the conferencing server at a second receive time point, the first and second probe packets being smaller than the data packet; (3) receiving information encoding a first difference between the first and second transmit time points and a second difference between the first and second receive time points; and (4) based on the first and second differences, modifying a transmission parameter associated with data packets to be transmitted thereafter to the conferencing server.
摘要翻译：一种方法，包括（1）在第一发送时间点，在发送数据分组之前，通过网络连接将第一探测分组发送到会议服务器，所述第一探测分组在第一接收时间点到达所述会议服务器; （2）在第二发送时间点，在发送数据分组之后立即通过网络连接将第二探测分组发送到会议服务器，第二探测分组在第二接收时间点到达会议服务器，第一和第第二探测分组小于数据分组; （3）接收编码第一和第二发送时间点之间的第一差异的信息和第一和第二接收时间点之间的第二差值; 和（4）基于第一和第二差异，将与之后发送的数据分组相关联的传输参数修改为会议服务器。

6. 发明授权

US08428247B2 Echo mitigation in a conference call 有权
公开(公告)号：US08428247B2
公开(公告)日：2013-04-23
申请号：US12326756
申请日：2008-12-02
申请人： James C. Frauenthal , Michael P. O'Brien , Michael A. Ramalho , Gary A. Skrabutenas , Shmuel Shaffer , Steven L. Christenson
发明人： James C. Frauenthal , Michael P. O'Brien , Michael A. Ramalho , Gary A. Skrabutenas , Shmuel Shaffer , Steven L. Christenson
IPC分类号： H04M9/08
CPC分类号： H04M3/002 , H04B3/23 , H04M9/082
摘要： In an example embodiment, an example method is provided for echo mitigation in a conference call. In this method, a test audio signal is transmitted to a conference endpoint and as a result, an echo associated with the transmittal of the test audio signal is received. One or more parameters of the echo are then identified and an echo mitigation process is selected from multiple echo mitigation processes based on the identified parameters. The selected echo mitigation process is then applied.

7. 发明申请

US20130039497A1 SYSTEM AND METHOD FOR USING ENDPOINTS TO PROVIDE SOUND MONITORING 有权
标题翻译：使用终点提供声音监测的系统和方法
公开(公告)号：US20130039497A1
公开(公告)日：2013-02-14
申请号：US13205368
申请日：2011-08-08
申请人： Michael A. Ramalho , James C. Frauenthal , Brian A. Apgar
发明人： Michael A. Ramalho , James C. Frauenthal , Brian A. Apgar
IPC分类号： H04R29/00
CPC分类号： G08B13/1672 , G08B13/19684 , G08B13/19697 , H04R1/02 , H04R1/2834 , H04R5/02 , H04R17/00 , H04R27/00 , H04R2205/022 , H04R2217/01 , H04R2227/003 , H04S5/00
摘要： A method is provided in one example embodiment that includes monitoring a sound pressure level with an endpoint (e.g., an Internet Protocol (IP) phone), which is configured for communications involving end users; analyzing the sound pressure level to detect a sound anomaly; and communicating the sound anomaly to a sound classification module. The endpoint can be configured to operate in a low-power mode during the monitoring of the sound pressure level. In certain instances, the sound classification module is hosted by the endpoint. In other implementations, the sound classification module is hosted in a cloud network.
摘要翻译：在一个示例性实施例中提供了一种方法，该方法包括用端点（例如，因特网协议（IP）电话）来监测声压级，其被配置用于涉及终端用户的通信; 分析声压级检测声音异常; 并将声音异常传送到声音分类模块。端点可以配置为在监听声压级时以低功耗模式运行。在某些情况下，声音分类模块由端点托管。在其他实现中，声音分类模块托管在云网络中。

8. 发明授权

US07483701B2 System and method for handling media in a seamless handoff environment 有权
标题翻译：在无缝切换环境中处理媒体的系统和方法
公开(公告)号：US07483701B2
公开(公告)日：2009-01-27
申请号：US11056843
申请日：2005-02-11
申请人： Ramanathan T. Jagadeesan , Bich T. Nguyen , Andrew C. Chung , Michael A. Ramalho
发明人： Ramanathan T. Jagadeesan , Bich T. Nguyen , Andrew C. Chung , Michael A. Ramalho
IPC分类号： H04Q7/20
CPC分类号： H04W36/18 , H04L65/80 , H04W36/14 , H04W84/042 , H04W84/12 , H04W88/06
摘要： A method for handling media in a make-before-break handoff between wireless networks is provided that includes communicating with a mobile station to facilitate a session handoff between two call legs of a session. The method also includes identifying a relevant frame of one of the legs, performing a cross correlation operation, generating a delay difference estimate between the two legs, and performing a level difference estimation for the two legs.
摘要翻译：提供了一种用于在无线网络之间的断开切换之间处理媒体的方法，其包括与移动台进行通信以便于会话的两个呼叫支路之间的会话切换。该方法还包括识别腿中的一条的相关帧，执行互相关操作，产生两条腿之间的延迟差估计，以及执行两条腿的电平差估计。

9. 发明授权

US07408918B1 Methods and apparatus for lossless compression of delay sensitive signals 有权
标题翻译：延迟敏感信号的无损压缩方法和装置
公开(公告)号：US07408918B1
公开(公告)日：2008-08-05
申请号：US10268345
申请日：2002-10-07
申请人： Michael A. Ramalho
发明人： Michael A. Ramalho
IPC分类号： H04L12/28 , G10L19/00 , G10L21/00
CPC分类号： G10L19/00 , G10L19/0017
摘要： Methods and apparatus are provided for compressing delay sensitive signals. Frames including multiple samples of the delay sensitive signal are analyzed to determine characteristics associated with the frames, such as the range of quantization levels represented by the samples of the frames. The delay sensitive signal is then compressed by providing an anchor point is sent along with information for determining the variation of each sample from the anchor point.
摘要翻译：提供了用于压缩延迟敏感信号的方法和装置。分析包括延迟敏感信号的多个样本的帧以确定与帧相关联的特性，例如由帧的样本表示的量化级的范围。然后通过提供锚定点与延迟敏感信号一起发送，以及用于确定每个样本与锚点的变化的信息。

10. 发明授权

US08948058B2 System and method for improving audio quality during web conferences over low-speed network connections 有权
标题翻译：通过低速网络连接在网络会议期间提高音频质量的系统和方法
公开(公告)号：US08948058B2
公开(公告)日：2015-02-03
申请号：US13555371
申请日：2012-07-23
申请人： Michael A. Ramalho , Mihailo Zilovic , Laurent Kim-Huy Pham , Gary A. Skrabutenas
发明人： Michael A. Ramalho , Mihailo Zilovic , Laurent Kim-Huy Pham , Gary A. Skrabutenas
IPC分类号： H04L12/16
CPC分类号： H04L65/80 , H04L12/1818 , H04L65/403
摘要： A method that includes: (1) transmitting, at a first transmit time point, a first probe packet over a network connection to a conferencing server immediately before transmitting a data packet, the first probe packet arriving at the conferencing server at a first receive time point; (2) transmitting, at a second transmit time point, a second probe packet over the network connection to the conferencing server immediately after transmitting the data packet, the second probe packet arriving at the conferencing server at a second receive time point, the first and second probe packets being smaller than the data packet; (3) receiving information encoding a first difference between the first and second transmit time points and a second difference between the first and second receive time points; and (4) based on the first and second differences, modifying a transmission parameter associated with data packets to be transmitted thereafter to the conferencing server.
摘要翻译：一种方法，其包括：（1）在发送数据分组之前，在第一传输时间点将第一探测分组通过网络连接发送到会议服务器，所述第一探测分组以第一接收时间到达所述会议服务器点; （2）在第二发送时间点，在发送数据分组之后立即通过网络连接将第二探测分组发送到会议服务器，第二探测分组在第二接收时间点到达会议服务器，第一和第第二探测分组小于数据分组; （3）接收编码第一和第二发送时间点之间的第一差异的信息和第一和第二接收时间点之间的第二差值; 和（4）基于第一和第二差异，将与之后发送的数据分组相关联的传输参数修改为会议服务器。

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