专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

21. 发明申请

US20100115566A1 Fast Channel Change Request Processing 审中-公开
标题翻译：快速通道更改请求处理
公开(公告)号：US20100115566A1
公开(公告)日：2010-05-06
申请号：US12261175
申请日：2008-10-30
申请人： Raziel Haimi-Cohen
发明人： Raziel Haimi-Cohen
IPC分类号： H04N7/173
CPC分类号： H04N21/2393 , H04N7/17318 , H04N21/2668 , H04N21/4384 , H04N21/482 , H04N21/6402 , H04N21/6408
摘要： A fast channel change request is processed in a signal distribution system comprising a network element coupled between a user interface device and a fast channel change server. The network element detects a fast channel change request sent from the user interface device for processing by the fast channel change server, and takes an action based on the detected fast channel change request. The action is effective to permit alteration of at least one characteristic of a unicast transmission that would otherwise be provided to the user interface device responsive to the fast channel change request.
摘要翻译：在包括耦合在用户接口设备和快速频道改变服务器之间的网络元件的信号分配系统中处理快速频道改变请求。网络元件检测从用户接口设备发送的用于由快速频道改变服务器处理的快速频道改变请求，并且基于检测到的快速频道改变请求采取动作。该动作有效地允许响应于快速频道改变请求而改变否则将被提供给用户接口设备的单播传输的至少一个特性。

22. 发明授权

US06545616B1 Methods and apparatus for digital wireless text telephony 有权
标题翻译：数字无线文本电话的方法和装置
公开(公告)号：US06545616B1
公开(公告)日：2003-04-08
申请号：US09334017
申请日：1999-06-15
申请人： Raziel Haimi-Cohen
发明人： Raziel Haimi-Cohen
IPC分类号： H03M700
CPC分类号： H04W88/02 , H03M13/00 , H04M1/2475 , H04M11/066
摘要： A repeater for use in a digital wireless teletype-capable telephone receiver. The repeater includes a receiver for receiving an input signal and interpreting the input signal to identify Baudot characters represented by the input signal, and produce a receiver signal comprising identifications of the Baudot characters represented by the input signal. The repeater also comprises a transmitter which produces an output signal based on the receiver signal produced by the receiver. The transmitter generates the Baudot codes identified to it by the receiver. The repeater therefore removes distortion which may be present in the input signal.
摘要翻译：一种用于数字无线电传电话电话接收机的中继器。中继器包括接收器，用于接收输入信号并解释输入信号以识别由输入信号表示的波多特字符，并产生包括由输入信号表示的波特字符的标识的接收机信号。中继器还包括基于由接收机产生的接收机信号产生输出信号的发射机。发射机产生由接收机识别的波多代码。因此，中继器消除输入信号中可能存在的失真。

23. 发明授权

US06374221B1 Automatic retraining of a speech recognizer while using reliable transcripts 有权
标题翻译：自动重新训练语音识别器，同时使用可靠的成绩单
公开(公告)号：US06374221B1
公开(公告)日：2002-04-16
申请号：US09337229
申请日：1999-06-22
申请人： Raziel Haimi-Cohen
发明人： Raziel Haimi-Cohen
IPC分类号： G10L1514
CPC分类号： G10L15/063 , G10L2015/0631 , G10L2015/0635
摘要： Automatic retraining of a speech recognizer during its normal operation in conjunction with an electronic device responsive to the speech recognizer is addressed. In this retraining, stored trained models are retrained on the basis of recognized user utterances. Feature vectors, model state transitions, and tentative recognition results are stored upon processing and evaluation of speech samples of the user utterances. A reliable transcript is determined for later adaptation of a speech model, in dependence upon the user's successive behavior when interacting with the speech recognizer and the electronic device. For example, in a name dialing process, such a behavior can be manual or voice re-dialing of the same number or dialing of a different phone number, immediately aborting an established communication, or braking it after a short period of time. In dependence upon such a behavior, a transcript is select in correspondence to a user's first utterance or in correspondence to a user's second utterance, or both, or the tentative recognition result (or results) are determined to be uncertain and deemed not to be suitable for updating a model, or updating is performed with appropriate weighting to take into effect the level of uncertainty. Upon determination of a reliable transcript, a model adaptation is performed.
摘要翻译：解决了语音识别器在正常操作期间与响应于语音识别器的电子设备的自动重新训练。在这次再培训中，存储的训练模型是在认可的用户话语的基础上再培训的。特征向量，模型状态转换和临时识别结果存储在用户话语的语音样本的处理和评估中。根据用户在与语音识别器和电子设备进行交互时的连续行为，确定可靠的转录文件用于随后适应语音模型。例如，在名称拨号过程中，这样的行为可以是手动或语音重拨相同号码或拨打不同的电话号码，立即中止已建立的通信，或者在短时间内制动它。根据这样的行为，对应于用户的第一个发音或对应于用户的第二个话语或两者的选择，或者暂定的识别结果（或结果）被确定为不确定并被认为不合适用于更新模型，或者以适当的加权来执行更新，以实现不确定性的水平。在确定可靠的转录物时，执行模型适应。

24. 发明授权

US6009390A Technique for selective use of Gaussian kernels and mixture component weights of tied-mixture hidden Markov models for speech recognition 失效
标题翻译：用于选择性使用高斯内核的技术和用于语音识别的绑定混合隐马尔可夫模型的混合分量权重
公开(公告)号：US6009390A
公开(公告)日：1999-12-28
申请号：US927883
申请日：1997-09-11
申请人： Sunil K. Gupta , Raziel Haimi-Cohen , Frank K. Soong
发明人： Sunil K. Gupta , Raziel Haimi-Cohen , Frank K. Soong
IPC分类号： G10L15/14 , G10L7/08
CPC分类号： G10L15/144
摘要： In a speech recognition system, tied-mixture hidden Markov models (HMMs) are used to match, in the maximum likelihood sense, the phonemes of spoken words given the acoustic input thereof. In a well known manner, such speech recognition requires computation of state observation likelihoods (SOLs). Because of the use of HMMs, each SOL computation involves a substantial number of Gaussian kernels and mixture component weights. In accordance with the invention, the number of Gaussian kernels is cut down to reduce the computational complexity and increase the efficiency of memory access to the kernels. For example, only the non-zero mixture component weights and the Gaussian kernels associated therewith are considered in the SOL computation. In accordance with an aspect of the invention, only a subset of the Gaussian kernels of significant values, regardless of the values of the associated mixture component weights, are considered in the SOL computation. In accordance with another aspect of the invention, at least some of the mixture component weights are quantized to reduce memory space needed to store them. As such, the computational complexity and memory access efficiency are further improved.
摘要翻译：在语音识别系统中，绑定混合隐马尔可夫模型（HMM）用于在最大似然意义上匹配给定其声输入的口语字的音素。以众所周知的方式，这种语音识别需要计算状态观察可能性（SOLs）。由于使用HMM，每个SOL计算涉及大量高斯核和混合分量权重。根据本发明，削减高斯内核的数量以减少计算复杂度并提高对内核的存储器访问的效率。例如，在SOL计算中仅考虑非零混合分量权重和与其相关联的高斯内核。根据本发明的一个方面，在SOL计算中仅考虑与有关混合分量权重值相关的有效值的高斯核的子集。根据本发明的另一方面，至少部分混合组分权重被量化以减少存储它们所需的存储空间。因此，计算复杂度和存储器访问效率进一步提高。

25. 发明授权

US5983093A Wireless terminal and wireless telecommunications system adapted to prevent the theft of wireless service 失效
标题翻译：无线终端和无线电信系统适用于防止无线服务被盗
公开(公告)号：US5983093A
公开(公告)日：1999-11-09
申请号：US906817
申请日：1997-08-06
申请人： Raziel Haimi-Cohen
发明人： Raziel Haimi-Cohen
IPC分类号： H04W12/00 , H04Q7/20
CPC分类号： H04W12/12 , H04L63/083 , H04W12/06
摘要： A wireless terminal and wireless telecommunications system are disclosed that prevent a thief of a wireless terminal from using the stolen wireless terminal to steal wireless service. A PIN is stored in the wireless terminal and the wireless terminal itself checks that a candidate PIN matches the stored PIN before the wireless terminal will initiate a call or will establish an incoming call. Thereafter, however, the user is permitted to call that telephone number or to receive a call from that telephone number without having to enter a candidate PIN again.In the wireless telecommunications system, a PIN is stored in a subscriber database for each user. The subscriber database also contains a history list of the telephone numbers that each user has previously called or received calls from. When the user first attempts to call a telephone number from which a received call has not been established, the wireless telecommunications system requires the user to enter a candidate PIN that matches the stored PIN before the call is established. Thereafter, the user is permitted to call that telephone number or receive a call from that telephone number without having to enter a candidate PIN again. Alternatively, when the user first receives a call from a telephone number that the user has not previously called, the wireless telecommunications system requires the user to enter a candidate PIN that matches the stored PIN before the call is established. Thereafter, the user is permitted to call that telephone number or receive a call from that telephone number without having to enter a candidate PIN again.
摘要翻译：公开了一种无线终端和无线电信系统，其防止无线终端的窃贼使用被盗的无线终端窃取无线服务。 PIN被存储在无线终端中，并且无线终端本身在无线终端发起呼叫之前检查候选PIN与存储的PIN是否匹配，或将建立来话呼叫。然而，此后，允许用户呼叫该电话号码或从该电话号码接收呼叫，而不必再次输入候选PIN。在无线电信系统中，每个用户将PIN存储在用户数据库中。用户数据库还包含每个用户先前已经呼叫或接收到呼叫的电话号码的历史列表。当用户首先尝试呼叫尚未建立接收呼叫的电话号码时，无线电信系统要求用户在呼叫建立之前输入与存储的PIN匹配的候选PIN。此后，允许用户呼叫该电话号码或从该电话号码接收呼叫，而不必再次输入候选PIN。或者，当用户首先从用户以前没有呼叫的电话号码接收到呼叫时，无线电信系统要求用户在呼叫建立之前输入与存储的PIN匹配的候选PIN。此后，允许用户呼叫该电话号码或从该电话号码接收呼叫，而不必再次输入候选PIN。

26. 发明授权

US5737724A Speech recognition employing a permissive recognition criterion for a repeated phrase utterance 失效
标题翻译：语音识别采用重复的短语发音的允许识别标准
公开(公告)号：US5737724A
公开(公告)日：1998-04-07
申请号：US695140
申请日：1996-08-08
申请人： Bishnu Saroop Atal , Raziel Haimi-Cohen , David Bjorn Roe
发明人： Bishnu Saroop Atal , Raziel Haimi-Cohen , David Bjorn Roe
IPC分类号： G10L15/00 , G10L15/08 , G10L15/10 , G10L15/22 , G10L15/28 , G01L5/06
CPC分类号： G10L15/10 , G10L2015/088
摘要： The invention relates to a method and apparatus for speech recognition, the speech to be recognized including one or more words. Recognition is based on an analysis of a first and a second utterance. In accordance with the invention, the first utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. The model of speech which most closely matches the first utterance is determined based on the one or more similarity metrics. The similarity metric corresponding to the most closely matching model of speech is analyzed to determine whether the similarity metric satisfies a first recognition criterion. The second utterance is compared to one or more models of speech associated with the most closely matching model (which may include the most closely matching model) to determine a second utterance similarity metric for each such comparison. The one or more second utterance similarity metrics are analyzed to determine whether the one or more metrics satisfies a second recognition criteria. The second utterance is recognized has the phrase corresponding to the most closely matching model of speech when the first and second recognition criteria are satisfied. The present invention has application to many problems in speech recognition including isolated word recognition and command spotting. An illustrative embodiment of the invention in the context of a cellular telephone is provided. Other embodiments are also discussed.
摘要翻译：本发明涉及用于语音识别的方法和装置，要识别的语音包括一个或多个单词。识别是基于对第一和第二话语的分析。根据本发明，将第一话语与一个或多个语音模型进行比较，以确定每个这样的比较的相似性度量。基于一个或多个相似性度量来确定与第一个发音最匹配的语音模型。分析对应于最接近匹配的语音模型的相似性度量，以确定相似性度量是否满足第一识别标准。将第二个话语与与最接近匹配的模型（其可以包括最接近匹配的模型）相关联的一个或多个语音模型进行比较，以确定每个这样的比较的第二话语相似性度量。分析一个或多个第二话语相似性度量以确定一个或多个度量是否满足第二识别标准。当满足第一和第二识别标准时，第二个话语被识别具有对应于最接近匹配的语音模型的短语。本发明可以应用于语音识别中的许多问题，包括孤立词识别和指令识别。提供了在蜂窝式电话机上的本发明的说明性实施例。还讨论了其他实施例。

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