-
公开(公告)号：US20130060571A1
公开(公告)日：2013-03-07
申请号：US13224778
申请日：2011-09-02
IPC分类号： G10L15/00
摘要： A system for integrating local speech recognition with cloud-based speech recognition in order to provide an efficient natural user interface is described. In some embodiments, a computing device determines a direction associated with a particular person within an environment and generates an audio recording associated with the direction. The computing device then performs local speech recognition on the audio recording in order to detect a first utterance spoken by the particular person and to detect one or more keywords within the first utterance. The first utterance may be detected by applying voice activity detection techniques to the audio recording. The first utterance and the one or more keywords are subsequently transferred to a server which may identify speech sounds within the first utterance associated with the one or more keywords and adapt one or more speech recognition techniques based on the identified speech sounds.
摘要翻译： 描述了一种用于将本地语音识别与基于云的语音识别相结合以提供有效的自然用户界面的系统。 在一些实施例中，计算设备确定与环境内的特定人员相关联的方向，并且生成与该方向相关联的音频记录。 然后，计算设备在音频记录上执行本地语音识别，以便检测特定人员所说出的第一话语，并检测第一话语内的一个或多个关键字。 可以通过将语音活动检测技术应用于音频记录来检测第一话语。 第一话语和一个或多个关键字随后被转移到可以识别与该一个或多个关键词相关联的第一话语内的语音的服务器，并且基于所识别的语音来调整一个或多个语音识别技术。
-
公开(公告)号：US08660847B2
公开(公告)日：2014-02-25
申请号：US13224778
申请日：2011-09-02
IPC分类号： G10L15/00
摘要： A system for integrating local speech recognition with cloud-based speech recognition in order to provide an efficient natural user interface is described. In some embodiments, a computing device determines a direction associated with a particular person within an environment and generates an audio recording associated with the direction. The computing device then performs local speech recognition on the audio recording in order to detect a first utterance spoken by the particular person and to detect one or more keywords within the first utterance. The first utterance may be detected by applying voice activity detection techniques to the audio recording. The first utterance and the one or more keywords are subsequently transferred to a server which may identify speech sounds within the first utterance associated with the one or more keywords and adapt one or more speech recognition techniques based on the identified speech sounds.
摘要翻译： 描述了一种用于将本地语音识别与基于云的语音识别相结合以提供有效的自然用户界面的系统。 在一些实施例中，计算设备确定与环境内的特定人员相关联的方向，并且生成与该方向相关联的音频记录。 然后，计算设备在音频记录上执行本地语音识别，以便检测特定人员所说出的第一话语，并检测第一话语内的一个或多个关键字。 可以通过将语音活动检测技术应用于音频记录来检测第一话语。 第一话语和一个或多个关键字随后被转移到可以识别与该一个或多个关键词相关联的第一话语内的语音的服务器，并且基于所识别的语音来调整一个或多个语音识别技术。
-
公开(公告)号：US20120310766A1
公开(公告)日：2012-12-06
申请号：US13483671
申请日：2012-05-30
申请人： Leo Soong
发明人： Leo Soong
IPC分类号： G06Q30/08
CPC分类号： G06Q30/08
摘要： A system and method of conducting an electronic auction allows participants to create multivariable auctions for participants having different locations having a positive or negative need of auctioned goods. The system may create initial bids to beat for all participants after the system calculates current costs relevant to each participant. After each bid, the system reviews the position or state of all participants, and outputs bids to beat that would result in an economic gain for the respective participants. The system may be configured to generate maps for the transport of goods and initial transport prices by acceptance of data from transportation bidders. After completion of an auction, a full system audit trail may be made available to verify the integrity of the auction and fees charged by the system. In a construction site embodiment, quarries may be integral partners and assist in establishing initial or default bids.
摘要翻译： 进行电子拍卖的系统和方法允许参与者为具有不同位置的参与者创建多变量拍卖，具有拍卖商品的正面或负面需求。 在系统计算与每个参与者相关的当前成本后，系统可以为所有参与者创建初始出价。 每次投标后，系统会检查所有参与者的职位或状态，并输出竞标，从而为各参与者带来经济收益。 该系统可以被配置为通过接受运输投标者的数据来生成运输货物和初始运输价格的地图。 拍卖完成后，可以提供完整的系统审核追踪，以验证拍卖的完整性和系统收取的费用。 在施工现场的实施例中，采石场可能是不可或缺的合作伙伴，并协助建立起始或默认出价。
-
-
搜索结果
3 条记录 (耗时 0.022 秒)
