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. 发明授权

US5257186A Digital computing apparatus for preparing document text 失效
标题翻译：用于准备文本文本的数字计算设备
公开(公告)号：US5257186A
公开(公告)日：1993-10-26
申请号：US702809
申请日：1991-05-21
申请人： Teruhiko Ukita , Kazuo Sumita , Satoshi Kinoshita
发明人： Teruhiko Ukita , Kazuo Sumita , Satoshi Kinoshita
IPC分类号： G06F17/21 , G06F17/24 , G06F17/27 , G06F17/30 , G06F15/38
CPC分类号： G06F17/27 , G06F17/24 , G06F17/2745 , G06F17/30696
摘要： A digital computing apparatus for preparing document text includes a sentence significance decision section for calculating a significance value of each sentence of document data according to a relation between each sentence and other sentences of the document data. The apparatus can also include a topic extraction section for extracting a topic for each sentence of the document data. A format structure extraction section extracts format structure from document data according to predetermined rules. The format structure, corresponding sentence significance values and topics are sent to an output section. The output section displays this information to the user. The sentence retrieval section retrieves sentences including a user inputted reference word from document data. Then the sentence retrieval section selects a sentence which is related to the reference word from retrieved sentences according to the sentence significance value or the topic. The output section displays only the selected sentence to user.
摘要翻译：用于准备文本文本的数字计算装置包括句子有效性判定部分，用于根据每个句子与文档数据的其他句子之间的关系来计算文档数据的每个句子的显着性值。该装置还可以包括用于提取文档数据的每个句子的主题的主题提取部分。格式结构提取部根据规定的规则从文档数据中提取格式结构。格式结构，相应的句子意义值和主题被发送到输出部分。输出部分向用户显示此信息。句子检索部分从文档数据中检索包括用户输入的参考词的句子。然后，句子检索部分根据句子的意义值或主题，从检索到的句子中选择与参考词相关的句子。输出部分只显示所选句子给用户。

2. 发明授权

US4723290A Speech recognition apparatus 失效
标题翻译：语音识别装置
公开(公告)号：US4723290A
公开(公告)日：1988-02-02
申请号：US608208
申请日：1984-05-08
申请人： Sadakazu Watanabe , Teruhiko Ukita
发明人： Sadakazu Watanabe , Teruhiko Ukita
IPC分类号： G10L15/00 , G10L15/02 , G10L15/10 , G10L5/00
CPC分类号： G10L15/10
摘要： Speech recognition is improved by first recognizing a sequence of phonemes, then generating a compatibility coefficient between two continuous phonemes to modify the similarity measurements. The compatibility coefficient is varied for a plurality of modified similarity measurements to further improve recognition accuracy.
摘要翻译：通过首先识别音素序列，然后产生两个连续音素之间的相容性系数来修改相似度测量来改善语音识别。为了进一步提高识别精度，对于多个修改的相似度测量来改变兼容性系数。

3. 发明授权

US4677673A Continuous speech recognition apparatus 失效
标题翻译：连续语音识别装置
公开(公告)号：US4677673A
公开(公告)日：1987-06-30
申请号：US563755
申请日：1983-12-21
申请人： Teruhiko Ukita , Tsuneo Nitta , Sadakazu Watanabe
发明人： Teruhiko Ukita , Tsuneo Nitta , Sadakazu Watanabe
IPC分类号： G10L11/00 , G10L15/00 , G10L15/10 , G10L5/00
CPC分类号： G10L15/00
摘要： Continuous speech signal is recognized using "rough" and "detail" parameters derived from prestored reference speech and current unknown speech. The detail parameters are 16 spectral coefficients, the rough parameters 2 or 4 spectral coefficients representing the signal. A word interval detector decides segmentation based on rough parameter similarity.
摘要翻译：使用从预存储的参考语音和当前未知语音导出的“粗略”和“详细”参数识别连续语音信号。详细参数是16个频谱系数，粗略参数2或4个表示信号的频谱系数。字间隔检测器根据粗略的参数相似度来决定分割。

4. 发明授权

US5742745A Communication device 失效
公开(公告)号：US5742745A
公开(公告)日：1998-04-21
申请号：US447652
申请日：1995-05-23
申请人： Akihiko Sugikawa , Yasuhiro Morioka , Teruhiko Ukita
发明人： Akihiko Sugikawa , Yasuhiro Morioka , Teruhiko Ukita
IPC分类号： G06F3/14 , G06F3/048 , H04L12/18 , H04L12/28 , H04L29/06 , H04L29/08 , H04L12/56
CPC分类号： H04L12/1813 , H04L29/06 , H04L67/14 , H04L67/16 , H04L67/42
摘要： The data processing device 400 of this invention comprises a controller unit 402, a data recorder unit 404, a display unit 406, a data input unit 408 and a communication control unit 410. By transmitting a request for service in a multiple-address way to a plurality of devices on a network and selecting a service providing device, communicability with the service-providing group can be automatically obtained without prior registration of device information in the respective devices or in any specified device. If the service providing device withdraws from the network or a trouble develops in the communication link, a new service providing device is selected from among other communicable devices.

5. 发明授权

US4677672A Continuous speech recognition apparatus 失效
标题翻译：连续语音识别装置
公开(公告)号：US4677672A
公开(公告)日：1987-06-30
申请号：US563505
申请日：1983-12-20
申请人： Teruhiko Ukita , Tsuneo Nitta
发明人： Teruhiko Ukita , Tsuneo Nitta
IPC分类号： G10L11/00 , G10L15/10 , G10L15/12 , G10L5/00
CPC分类号： G10L15/12
摘要： A continuous speech recognition circuit has a data generating circuit for calculating feature pattern data each having N-frame feature parameter data of a plurality of word-periods and reference pattern data every time one-frame period has elapsed and for sequentially generating a maximal similarity data among the calculated similarity data, and a recognition circuit for detecting a series of continuous word-periods which gives the largest similarity sum within a speech interval in accordance with the similarity data from the data generating circuit and recognizing as effective word data the word series corresponding to the detected series of continuous word-periods. The similarity data in each word period is obtained by calculating partial similarity data between the feature parameter data of each frame and each reference parameter data and using the N partial similarity data obtained during the word-period.
摘要翻译：连续语音识别电路具有数据生成电路，用于在每一个时间段经过时，计算出具有多个字周期的N帧特征参数数据和参考图形数据的特征图形数据，并且顺次生成最大相似度数据在所计算的相似度数据中，以及识别电路，用于根据来自数据生成电路的相似度数据，检测在语音间隔内给出最大相似度和的一系列连续字周期，并且识别作为有效字数据的字串对应到所检测的连续字期的一系列。通过计算每个帧的特征参数数据和每个参考参数数据之间的部分相似度数据并使用在单词周期期间获得的N个部分相似度数据来获得每个单词周期中的相似度数据。

6. 发明授权

US5949772A Communication device 失效
标题翻译：通讯设备
公开(公告)号：US5949772A
公开(公告)日：1999-09-07
申请号：US967904
申请日：1997-11-12
申请人： Akihiko Sugikawa , Yasuhiro Morioka , Teruhiko Ukita
发明人： Akihiko Sugikawa , Yasuhiro Morioka , Teruhiko Ukita
IPC分类号： G06F3/14 , G06F3/048 , H04L12/18 , H04L12/28 , H04L29/06 , H04L29/08 , H04Q7/00
CPC分类号： H04L12/1813 , H04L29/06 , H04L67/14 , H04L67/16 , H04L67/42
摘要： The data processing device 400 of this invention comprises a controller unit 402, a data recorder unit 404, a display unit 406, a data input unit 408 and a communication control unit 410. By transmitting a request for service in a multiple-address way to a plurality of devices on a network and selecting a service providing device, communicability with the service-providing group can be automatically obtained without prior registration of device information in the respective devices or in any specified device. If the service providing device withdraws from the network or a trouble develops in the communication link, a new service providing device is selected from among other communicable devices.
摘要翻译：本发明的数据处理装置400包括控制器单元402，数据记录单元404，显示单元406，数据输入单元408和通信控制单元410.通过以多地址方式发送服务请求到网络上的多个设备和选择服务提供设备，可以自动获得与服务提供组的通信性，而无需在各个设备或任何指定设备中事先注册设备信息。如果服务提供装置从网络退出或在通信链路中发生故障，则从其他可通信装置中选择新的服务提供装置。

7. 发明授权

US4987596A Knowledge-guided automatic speech recognition apparatus and method 失效
标题翻译：知识指导自动语音识别装置及方法
公开(公告)号：US4987596A
公开(公告)日：1991-01-22
申请号：US546709
申请日：1990-06-29
申请人： Teruhiko Ukita
发明人： Teruhiko Ukita
IPC分类号： G10L11/00 , G10L15/00 , G10L15/04 , G10L15/10 , G10L15/18
CPC分类号： G10L15/00
摘要： An acoustic pattern of continuous input speech is divided by an acoustic analyzer into frames of a predetermined time interval. A similarity calculator calculates similarities between frame data and the reference phonemic labels prestored in a dictionary memory, and supplies similarity data to a main processor, which has memories prestores speech duration data and connectability data. The main processor extracts, from among the references phonemic labels, those which satisfy phonetic/phonological conditions with respect to phonemes of the input speech. Similarity sum calculation is conducted only for the similarity data of the extracted labels.
摘要翻译：连续输入语音的声学图案由声学分析器划分成预定时间间隔的帧。相似度计算器计算帧数据和预先存储在字典存储器中的参考音素标签之间的相似度，并将相似性数据提供给主处理器，该主处理器具有预存着语音持续时间数据和可连接性数据的存储器。主处理器从参考音素标签中提取了与输入语音的音素相符的语音/语音条件。对所提取标签的相似性数据进行相似和计算。

8. 发明授权

US5771352A Communication control apparatus and method 失效
标题翻译：通信控制装置及方法
公开(公告)号：US5771352A
公开(公告)日：1998-06-23
申请号：US420851
申请日：1995-04-12
申请人： Makoto Nakamura , Yosuke Tajika , Akihiko Sugikawa , Masako Sato , Kazuaki Iwamura , Teruhiko Ukita
发明人： Makoto Nakamura , Yosuke Tajika , Akihiko Sugikawa , Masako Sato , Kazuaki Iwamura , Teruhiko Ukita
IPC分类号： H04L12/28 , H04B1/00
CPC分类号： H04W4/08
摘要： Communication control apparatus capable of communicating among plural users when the plural users bring respective equipment into proximity of each other includes a transmission section to transmit terminal discriminating information to discriminate a particular terminal. A receiving section receives terminal discriminating information transmitted by another terminal or terminals. A discrimination section discriminates other terminal(s) capable of communicating with the particular terminal in accordance with the terminal discriminating information received by the receiving section. A group-set section sets one terminal or plural terminals among terminals discriminated by the discrimination means as members of the same group. An information sending section sends the same information to the terminals set by the group-set means.
摘要翻译：当多个用户将各个设备彼此接近时，能够在多个用户之间进行通信的通信控制装置包括：发送部，用于发送终端识别信息，以区分特定的终端。接收部分接收由另一终端发送的终端识别信息。鉴别部分根据由接收部分接收到的终端鉴别信息来区分能够与特定终端进行通信的其他终端。组合部分将鉴别装置识别的终端中的一个终端或多个终端设置为同一组的成员。信息发送部将相同的信息发送到由组集装置设定的终端。

9. 发明授权

US4924518A Phoneme similarity calculating apparatus 失效
标题翻译：音素相似度计算装置
公开(公告)号：US4924518A
公开(公告)日：1990-05-08
申请号：US133808
申请日：1987-12-16
申请人： Teruhiko Ukita
发明人： Teruhiko Ukita
IPC分类号： G10L15/10 , G10L15/00
CPC分类号： G10L15/00
摘要： Continuous speech is input to an acoustic analyzer comprising a filter bank which filters (acoustically analyzes) the input speech and outputs from each filter a characteristic parameter vector of the input speech. The acoustic analyzer also calculates a steadiness parameter which is proportional to a reciprocal of a change in the spectrum of the input speech and represents steadiness of the input speech. the feature parameter vector is input to an initial similarity calculator, and a similarity (initial similarity) to each reference phoneme pattern stored in a reference phoneme pattern memory is calculated using a multiple similarity method. The initial similarity is input to a similarity normalizing circuit, and is normalized (weighted) based on the steadiness parameter in order to reflect information representing steadiness or unsteadiness of a phoneme into the similarity. For a steady reference phoneme, weighting is increased when the steadiness parameter increases and is decreased when the steadiness parameter decreases. For an unsteady reference phoneme, weighting is increased when the steadiness parameter decreases and is decreased when the steadiness parameter increases.
摘要翻译：将连续语音输入到包括滤波器组的声学分析器，该滤波器组对输入语音进行滤波（声学分析），并且从每个滤波器输出输入语音的特征参数矢量。声学分析器还计算与输入语音的频谱的变化的倒数成比例的稳定参数，并且表示输入语音的稳定性。将特征参数矢量输入到初始相似度计算器，并且使用多重相似度方法来计算存储在参考音素模式存储器中的每个参考音素模式的相似度（初始相似度）。将初始相似性输入到相似性归一化电路，并且基于稳定性参数被归一化（加权），以便将表示音素的稳定性或不稳定性的信息反映到相似性中。对于稳定参考音素，当稳定参数增加时，加权增加，并且当稳定参数降低时，加权减小。对于不稳定参考音素，当稳定参数降低时，加权增加，并且当稳定参数增加时减小。

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