-
公开(公告)号：US6137867A
公开(公告)日：2000-10-24
申请号：US78733
申请日：1998-05-14
IPC分类号： H04M11/00
摘要： An interactive method for composing an alphanumeric message by a caller using a telephone keypad includes storing (215) a lexical database (135) from which unigram probabilities, forward conditional probabilities, and backward conditional probabilities for a plurality of words can be recovered; storing a received sequence of key codes (405) representing a sequence in which keys on a telephone style keypad are keyed; generating a word trellis including candidate words (415) derived from the sequence and the lexical database; determining a most likely phrase (420) from the candidate words, the unigram probabilities, forward conditional probabilities, and backward conditional probabilities; generating a most likely message (425) from the most likely phrase and presenting the most likely message to the caller; and confirming that the most likely message is the alphanumeric message (430).
-
2.发明授权Voice compression by phoneme recognition and communication of phoneme indexes and voice features 失效语音压缩由音素识别和通信的音素指标和语音特征
公开(公告)号：US6073094A
公开(公告)日：2000-06-06
申请号：US89081
申请日：1998-06-02
CPC分类号： G10L19/0018
摘要： A communication system includes a transmitter for transmitting messages to a plurality of receiving devices of the communication system, and a processing system. The processing system is adapted to convert a caller's voice message to a sequence of phonemes whereby the caller's voice message is intended for a receiving device. To accomplish the conversion, steps of Fourier transform, spectral subdivision, envelope filtering autocorrelation function determination of each subdivision, and voiceness determination for each subdivision are performed. The processing system is further adapted to generate a sequence of phoneme indexes and voice features corresponding to the sequence of phonemes, and to cause the transmitter to transmit the sequence of phoneme indexes to the receiving device for generating a voice signal representative of the caller's voice message. The voice features can include spectral features, average energy, duration, and pitch to improve the quality of the voice signal. The receiving device can be a selective call radio.
摘要翻译： 通信系统包括用于向通信系统的多个接收设备发送消息的发射机和处理系统。 处理系统适于将呼叫者的语音消息转换成一系列音素，由此呼叫者的语音消息用于接收设备。 为了完成转换，执行傅立叶变换，频谱细分，每个细分的包络滤波自相关函数确定步骤和每个细分的声音确定步骤。 该处理系统进一步适用于产生与音素序列相对应的音素索引和语音特征序列，并使发射机将音素索引序列发射到接收装置，以产生代表呼叫者语音消息的语音信号 。 语音特征可以包括频谱特征，平均能量，持续时间和音高以提高语音信号的质量。 接收设备可以是选呼通话。
-
公开(公告)号：US06052443A
公开(公告)日：2000-04-18
申请号：US166739
申请日：1998-10-05
CPC分类号： G06F3/0237 , H04M2250/70
摘要： An interactive method for composing an alphanumeric message by a caller using a telephone keypad includes storing (215) a lexical database (135) from which unigram probabilities, forward conditional probabilities, and backward conditional probabilities for a plurality of words can be recovered; storing a received sequence of key codes (405) representing a sequence in which keys on a telephone style keypad are keyed; generating a word trellis including candidate words (415) derived from the sequence and the lexical database; determining a most likely phrase (420) from the candidate words, the unigram probabilities, forward conditional probabilities, and backward conditional probabilities; generating a most likely message (425) from the most likely phrase and presenting the most likely message to the caller; and confirming that the most likely message is the alphanumeric message (430).
摘要翻译： 一种用于使用电话键盘由呼叫者构成字母数字消息的交互方法包括存储（215）词法数据库（135），可从中恢复多个单词的单位概率，前向条件概率和反向条件概率; 存储表示键盘键盘上的键的序列的接收的键码序列（405）; 生成包括从序列导出的候选词（415）和词汇数据库的单词格; 从所述候选词确定最可能的短语（420），所述单字组概率，前向条件概率和向后条件概率; 从最可能的短语产生最可能的消息（425），并向呼叫者呈现最可能的消息; 并确认最可能的消息是字母数字消息（430）。
-
公开(公告)号：US5974121A
公开(公告)日：1999-10-26
申请号：US108828
申请日：1998-07-01
IPC分类号： H04M11/00
CPC分类号： H04M11/022
摘要： An interactive method for composing an alphanumeric message by a caller using a telephone keypad includes storing (215) a lexical database (135) from which unigram probabilities, forward conditional probabilities, and backward conditional probabilities for a plurality of words can be recovered; storing a received sequence of key codes (405) representing a sequence in which keys on a telephone style keypad are keyed; generating a word trellis including candidate words (415) derived from the sequence and the lexical database; determining a most likely phrase (420) from the candidate words, the unigram probabilities, forward conditional probabilities, and backward conditional probabilities; generating a most likely message (425) from the most likely phrase and presenting the most likely message to the caller; and confirming that the most likely message is the alphanumeric message (430).
-
5.发明授权Subband normalization, transformation, and voiceness to recognize phonemes for text messaging in a radio communication system 失效子带规范化，转换和语音识别无线电通信系统中文本消息的音素
公开(公告)号：US6163765A
公开(公告)日：2000-12-19
申请号：US50184
申请日：1998-03-30
申请人： Oleg Andric , Lu Chang , Jian-Cheng Huang , Arthur Gerald Herkert
发明人： Oleg Andric , Lu Chang , Jian-Cheng Huang , Arthur Gerald Herkert
CPC分类号： H04W4/18 , G10L15/02 , G10L2015/025 , G10L2025/937 , H04W4/14
摘要： A radio communication system includes a voice recognition system (221) for converting (400) a caller's voice message to a textual speech message. The textual speech message is then transmitted to an intended selective call radio (122). To perform these functions, the radio communication system includes a caller interface circuit (218), a transmitter (116), and a processor (222). To perform voice-to-text conversion, the processor is adapted to cause the caller interface circuit to sample a voice signal generated by the caller during a plurality of frame intervals, and to apply a Fourier transform thereto, thereby generating spectral data. The spectral data is subdivided into a plurality of bands. The spectral envelope of the spectral data is then filtered out to generate filtered spectral data. A Fourier transform is applied thereto to generate an autocorrelation function for each band. From the autocorrelation function of each band, a magnitude is determined, which is representative of the degree of voiceness of each band. The degree of voiceness for each band is then applied to a corresponding plurality of phoneme models, which are used to derive a textual equivalent of speech from the voice signal. The textual equivalent of speech is then transmitted to the selective call radio by way of the transmitter.
摘要翻译： 无线电通信系统包括用于将呼叫者的语音消息转换（400）到文本语音消息的语音识别系统（221）。 然后将文本语音消息发送到预期的选择呼叫无线电（122）。 为了执行这些功能，无线电通信系统包括呼叫者接口电路（218），发射器（116）和处理器（222）。 为了执行语音到文本转换，处理器适于使呼叫者接口电路在多个帧间隔期间采样由呼叫者产生的语音信号，并对其进行傅里叶变换，由此产生频谱数据。 光谱数据被细分成多个频带。 然后滤出光谱数据的光谱包络以产生滤波的光谱数据。 对其进行傅立叶变换以产生每个频带的自相关函数。 根据每个频带的自相关函数，确定一个幅度，其代表每个频带的声音程度。 然后将每个频带的声音程度应用于相应的多个音素模型，这些音素模型用于从语音信号中导出语音的文本等价物。 然后通过发射机将语音的文本等价物发送到选呼通话。
-
6.发明授权
公开(公告)号：US5692019A
公开(公告)日：1997-11-25
申请号：US664747
申请日：1996-06-17
申请人： Chun-Ye Susan Chang , Jian-Cheng Huang , Lu Chang , Lorenzo Ponce De Leon , David Petreye , James Michael Keba , Clinton C. Powell, II
发明人： Chun-Ye Susan Chang , Jian-Cheng Huang , Lu Chang , Lorenzo Ponce De Leon , David Petreye , James Michael Keba , Clinton C. Powell, II
摘要： A communication device (400) with a polarization diversity antenna configuration, having a first antenna (410) with a first plane of polarization and a second antenna (412) with a second plane of polarization. Signal strength of a demodulated signal when the antenna switch (420) is coupled to one of the antennas (410, 412) is measured by a signal strength measuring circuit (440) to generate a short-term average signal power (SA) representing signal strength over a first predetermined number of symbol periods, a medium-term average signal power (MA) representing signal strength over a second predetermined number of symbol periods, and a long-term average signal power (LA) representing signal strength over a third predetermined number of symbol periods, greater than the second predetermined number of symbol periods and first predetermined number of symbol periods. Switching between antennas (410, 412) is made in response to differences between SA, MA and LA.
摘要翻译： 具有极化分集天线配置的通信设备（400）具有具有第一偏振平面的第一天线（410）和具有第二偏振平面的第二天线（412）。 天线开关（420）耦合到天线（410,412）之一时的解调信号的信号强度由信号强度测量电路（440）测量，以产生表示信号的短期平均信号功率（SA） 超过第一预定数量的符号周期的强度，表示第二预定数量的符号周期的信号强度的中期平均信号功率（MA）以及表示超过第三预定数量的信号强度的长期平均信号功率（LA） 符号周期的数量，大于第二预定数量的符号周期和第一预定数量的符号周期。 响应于SA，MA和LA之间的差异，在天线（410,412）之间进行切换。
-
公开(公告)号：US20050013719A1
公开(公告)日：2005-01-20
申请号：US10607379
申请日：2003-06-26
CPC分类号： F01C1/077
摘要： This rotary piston engine is to propel twin or double twin pistons to do a rotational run in the round-section cylinder. The characteristic is when the stop-piston is locked, it cannot rotate until being unlocked. Another piece or pairs rotary pistons perform the four processes of the internal combustion engine. They are air absorption, compression, expansion and exhaustion.
摘要翻译： 该旋转活塞发动机是推动双或双双活塞在圆形气缸中进行旋转运行。 特点是当止动活塞被锁定时，它不能旋转直到被解锁。 另一个或两对旋转活塞执行内燃机的四个过程。 它们是空气吸收，压缩，膨胀和耗尽。
-
8.发明授权Automatic and attendant speech to text conversion in a selective call radio system and method 失效在选择性呼叫无线电系统和方法中自动和伴随语音转换文本
公开(公告)号：US6151572A
公开(公告)日：2000-11-21
申请号：US67779
申请日：1998-04-27
申请人： Yan-Ming Cheng , Lu Chang , Kenneth D. Finlon , Arthur G. Herkert
发明人： Yan-Ming Cheng , Lu Chang , Kenneth D. Finlon , Arthur G. Herkert
CPC分类号： H04M3/533 , H04M2201/40 , H04M2201/60
摘要： A radio communication system includes a voice recognition system (218), a transmitter (202) and a processing system (210). The voice recognition system is utilized for receiving caller initiated messages, and the transmitter is used for transmitting messages to a plurality of SCRs (selective call radios) (122) of the radio communication system. The processing system, which is coupled to the voice recognition system, and the transmitter, is adapted to cause the voice recognition system to convert a voice signal representative of a voice message originated by a caller of the radio communication system to a text message (401, 417), wherein the text message is intended for a SCR, to then generate a likelihood of success that the voice signal has been flawlessly converted to a text message, to have a human listen to an audible representation of the voice signal, and to cause the transmitter to transmit the text message to the SCR (432). The converting step includes autocorrelation by Fourier transform, measure a degree of voiceness for each band, applying the degree of voiceness to a corresponding plurality of phenome models, and deriving a text equivalent by searching through a phenome library.
摘要翻译： 无线电通信系统包括语音识别系统（218），发射机（202）和处理系统（210）。 语音识别系统被用于接收主叫方发起的消息，并且发射机用于向无线电通信系统的多个SCR（选择性呼叫无线电）（122）发送消息。 耦合到语音识别系统的处理系统和发射机适于使语音识别系统将表示由无线电通信系统的呼叫者发起的语音消息的语音信号转换成文本消息（401 ，417），其中所述文本消息旨在用于SCR，然后生成所述语音信号已经被完美地转换为文本消息的成功的可能性，以使人们听到所述语音信号的可听见的表示，并且 使发射机将文本消息发送到SCR（432）。 转换步骤包括通过傅立叶变换的自相关，测量每个频带的声音程度，将声音的程度应用于对应的多个表现模型，以及通过在phenome库中搜索来导出等价文本。
-
9.发明授权
公开(公告)号：US5592531A
公开(公告)日：1997-01-07
申请号：US415288
申请日：1995-04-03
申请人： Yan M. Cheng , Lu Chang
发明人： Yan M. Cheng , Lu Chang
CPC分类号： H04W88/185
摘要： A selective call communication system (100), such as a paging system (100), and a method therefor, for using a lexicon (134) for voice data entry in the selective call communication system (100) is shown. The system (100) associates a Voice User ID (206) to a subscriber ID (202) for one or more subscribers of the system (100). The system (100) accumulates user system statistics (208). Then, based on the accumulated user system statistics (208), the system (100) defines a lexicon (134) to include at least one Voice User ID (206) for the one or more subscribers for voice data entry for the system (100).
摘要翻译： 示出了用于在选呼通信系统（100）中使用语音数据输入的词典（134）的选呼通信系统（100），诸如寻呼系统（100）及其方法。 系统（100）将语音用户ID（206）与用于系统（100）的一个或多个订户的用户ID（202）相关联。 系统（100）累积用户系统统计（208）。 然后，基于累积的用户系统统计信息（208），系统（100）定义一个词典（134），以包含用于一个或多个用户的至少一个语音用户ID（206），用于系统的语音数据输入（100 ）。
-
公开(公告)号：US20190158799A1
公开(公告)日：2019-05-23
申请号：US15817043
申请日：2017-11-17
申请人： Xinting Gao , Wenshou Chen , Shan Xu , Yanfang Huang , Guansong Liu , Lu Chang
发明人： Xinting Gao , Wenshou Chen , Shan Xu , Yanfang Huang , Guansong Liu , Lu Chang
摘要： A multiple camera imaging system, comprising: a first camera image sensor configured to obtain a first image of a scene from a first vantage perspective point; a second camera image sensor configured to obtain a second image of the scene from a second vantage perspective point; and an image signal processor (ISP), configured to process the first image and the second image by performing the following steps: producing a first roughly-aligned image from the first image, and a second roughly-aligned image from the second image; using the first and second roughly-aligned images to produce a disparity image; identifying a feature point within the first roughly-aligned image; utilizing the disparity image to create a search zone within the second roughly-aligned image; and identifying a group of candidate feature points within the search zone; identifying within the search zone a best-matched candidate feature point that best matches the feature point within the first roughly-aligned image to form a best-matched feature point pair; and using information from the best-matched feature point pair to further align the first and second roughly-aligned images.
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.024 秒)
