-
公开(公告)号：US20080126100A1
公开(公告)日：2008-05-29
申请号：US11563835
申请日：2006-11-28
IPC分类号： G10L21/06
CPC分类号： G10L15/265 , G10L15/08 , G10L15/20
摘要： A speech recognition method includes the steps of receiving input speech containing vocabulary, processing the input speech with a grammar to obtain N-best hypotheses and associated parameter values, and determining whether a first-best hypothesis of the N-best hypotheses is confusable with any vocabulary within the grammar. The first-best hypothesis is accepted as recognized speech corresponding to the received input speech if the first-best hypothesis is not determined to be confusable with any vocabulary within the grammar. Where the first-best hypothesis is determined to be confusable, at least one parameter value of the first-best hypothesis can be compared to at least one threshold value. The first-best hypothesis can be accepted as recognized speech corresponding to the received input speech, if the parameter value of the first-best hypothesis is greater than the threshold value.
摘要翻译： 语音识别方法包括以下步骤：接收包含词汇的输入语音，用语法处理输入语音以获得N最佳假设和相关参数值，以及确定N最佳假设的第一最佳假设是否与任何 语法中的词汇。 如果第一最佳假设不被确定为与语法内的任何词汇混淆，则第一最佳假设被接受为对应于接收到的输入语音的公认语音。 在确定第一最佳假设是可混淆的情况下，可以将第一最佳假设的至少一个参数值与至少一个阈值进行比较。 如果第一最佳假设的参数值大于阈值，则第一最佳假设可被接受为对应于接收到的输入语音的识别语音。
-
2.发明授权Correcting substitution errors during automatic speech recognition by accepting a second best when first best is confusable 有权在自动语音识别期间纠正替代错误，首次接受第二好的时候是可混淆的公开(公告)号：US08600760B2
公开(公告)日：2013-12-03
申请号：US11563835
申请日：2006-11-28
CPC分类号： G10L15/265 , G10L15/08 , G10L15/20
摘要： A speech recognition method includes the steps of receiving input speech containing vocabulary, processing the input speech with a grammar to obtain N-best hypotheses and associated parameter values, and determining whether a first-best hypothesis of the N-best hypotheses is confusable with any vocabulary within the grammar. The first-best hypothesis is accepted as recognized speech corresponding to the received input speech if the first-best hypothesis is not determined to be confusable with any vocabulary within the grammar. Where the first-best hypothesis is determined to be confusable, at least one parameter value of the first-best hypothesis can be compared to at least one threshold value, and accepting the second-best as the recognized speech, if its confidence score is within certain lower and upper threshold values and is not confusable with the first-best. The first-best hypothesis can be accepted as recognized speech corresponding to the received input speech, if the parameter value of the first-best hypothesis is greater than the threshold value.
摘要翻译： 语音识别方法包括以下步骤：接收包含词汇的输入语音，用语法处理输入语音以获得N最佳假设和相关参数值，以及确定N最佳假设的第一最佳假设是否与任何 语法中的词汇。 如果第一最佳假设不被确定为与语法内的任何词汇混淆，则第一最佳假设被接受为对应于接收到的输入语音的公认语音。 在确定第一最佳假设是可混淆的情况下，可以将第一最佳假设的至少一个参数值与至少一个阈值进行比较，并且如果其置信度分数在 某些较低和较高的阈值，并且不能与第一好的混淆。 如果第一最佳假设的参数值大于阈值，则第一最佳假设可被接受为对应于接收到的输入语音的识别语音。
-
3.发明申请公开(公告)号：US20060132092A1
公开(公告)日：2006-06-22
申请号：US11017348
申请日：2004-12-20
申请人： Allan Hoffman , Edward Abeska , Scott Rush
发明人： Allan Hoffman , Edward Abeska , Scott Rush
IPC分类号： H02J7/00
CPC分类号： G01R31/3651 , G01R31/3648
摘要： Methods and apparatus are provided for estimating the remaining state-of-charge of a non-rechargeable power source, such as a back-up battery for an electronic module normally connected to a primary power source. A processor within the electronic module implements a prediction algorithm, in order to monitor the temperature of the back-up attery, and to calculate various current draws of the back-up battery. The processor adjusts the nominal self-discharge rate of the back-up battery in accordance with the measured temperatures, and calculates an adjusted self-discharge quantity. The processor also accumulates current draw data and reduces the initial state-of-charge value of the back-up battery by the temperature-adjusted self-discharge quantity and the cumulative current draw quantities to determine a remaining state-of-charge of the back-up battery. At a predetermined state-of-charge threshold level, an indicator can be activated to advise a user to replace the back-up battery.
摘要翻译： 提供了用于估计不可充电电源（例如通常连接到主电源的电子模块的备用电池）的剩余充电状态的方法和装置。 电子模块内的处理器实现预测算法，以便监视备用电源的温度，并计算备用电池的各种电流消耗。 处理器根据测量的温度调节备用电池的标称自放电率，并计算调整后的自放电量。 处理器还累积电流抽取数据，并通过温度调节的自放电量和累积电流抽取量来减小备用电池的初始充电状态值，以确定后端电池的剩余充电状态 - 电池。 在预定的充电阈值水平下，可以启动指示器以建议用户更换备用电池。
-
-
搜索结果
3 条记录 (耗时 0.016 秒)
