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

US20100063965A1 CONTENT PROCESSOR, CONTENT PROCESSING METHOD, AND CONTENT PROCESSING PROGRAM 审中-公开
标题翻译：内容处理器，内容处理方法和内容处理程序
公开(公告)号：US20100063965A1
公开(公告)日：2010-03-11
申请号：US12595346
申请日：2008-04-25
申请人： Ken Hanazawa , Masahiro Iwadare , Kyoji Hirata
发明人： Ken Hanazawa , Masahiro Iwadare , Kyoji Hirata
IPC分类号： G06F17/30
CPC分类号： G06F16/951
摘要： To provide a content processing technique which enables to prevent a reading person from easily guessing the fact of hiding and hidden information, and to obtain a content having natural information close to information of its original content before hiding. A content processor includes a search means which searches contents having information similar to a part excluding a part to be hidden in the original content, an arithmetic means which calculates non-similarity which shows the degree of non-similarity of each content obtained by the search means to the part to be hidden of the contend, and a selection means which selects the content which is the least similar to the part to be hidden out of the contents searched by the search means.
摘要翻译：提供一种内容处理技术，其能够防止阅读者容易地猜测隐藏和隐藏信息的事实，并且在隐藏之前获得具有接近其原始内容的信息的具有自然信息的内容。一种内容处理装置，包括搜索装置，该搜索装置搜索与除了原始内容中要隐藏的部分之外的部分相似的信息的内容;计算表示通过搜索获得的每个内容的非相似度程度的非相似度的算术装置指示要隐藏的部分的装置，以及选择装置，其从搜索装置搜索到的内容中选择与要隐藏的部分最不相似的内容。

22. 发明申请

US20090287488A1 TEXT DISPLAY, TEXT DISPLAY METHOD, AND PROGRAM 审中-公开
标题翻译：文本显示，文本显示方法和程序
公开(公告)号：US20090287488A1
公开(公告)日：2009-11-19
申请号：US12294318
申请日：2007-03-16
申请人： Ken Hanazawa
发明人： Ken Hanazawa
IPC分类号： G10L15/26
CPC分类号： G10L15/22 , G10L15/26 , G10L21/06 , H04N5/44513 , H04N21/4394 , H04N21/440236 , H04N21/4884
摘要： A text display in which speech information can be effectively conveyed in a text to the user. The text display comprises a speech input section (101) for inputting a speech, a storage section (130) in which a recognition dictionary for converting the speech information into a text is stored, an output section (105) for displaying the text, and a control section (120) for recognizing a word or a word line corresponding to a speech with reference to the recognition dictionary upon input of the speech and obtaining the result of the recognition including the word or the word line and its importance, computing the display time during which the result of the recognition is displayed in response to the importance, and allowing the output section to display the result of the recognition more than the computed display time.
摘要翻译：可以将文本中的语音信息有效传达给用户的文本显示。文本显示器包括用于输入语音的语音输入部分（101），存储部分（130），其中存储用于将语音信息转换为文本的识别词典，用于显示文本的输出部分（105），以及控制部分，用于在输入语音时参考识别词典识别对应于语音的单词或字线，并获得包括单词或字线的识别结果及其重要性，计算显示响应于重要性显示识别结果的时间，并且允许输出部分比所计算的显示时间显示更多的识别结果。

23. 发明授权

US08315870B2 Rescoring speech recognition hypothesis using prosodic likelihood 有权
标题翻译：使用韵律可能性解答语音识别假设
公开(公告)号：US08315870B2
公开(公告)日：2012-11-20
申请号：US12672015
申请日：2008-08-22
申请人： Ken Hanazawa
发明人： Ken Hanazawa
IPC分类号： G10L15/04
CPC分类号： G10L15/1807 , G10L15/187 , G10L25/15 , G10L2015/025
摘要： A distance calculation unit (16) obtains the acoustic distance between the feature amount of input speech and each phonetic model. A word search unit (17) performs a word search based on the acoustic distance and a language model including the phoneme and prosodic label of a word, and outputs a word hypothesis and a first score representing the likelihood of the word hypothesis. The word search unit (17) also outputs a vowel interval and its tone label in the input speech, when assuming that the recognition result of the input speech is the word hypothesis. A tone recognition unit (21) outputs a second score representing the likelihood of the tone label output from the word search unit (17) based on a feature amount corresponding to the vowel interval output from the word search unit (17). A rescore unit (22) corrects the first score of the word hypothesis output from the word search unit (17) using the second score output from the tone recognition unit (21). This allows to raise the speech recognition accuracy for tone speech.
摘要翻译：距离计算单元（16）获得输入语音的特征量与每个语音模型之间的声学距离。词搜索单元（17）基于声距进行词搜索和包括单词的音素和韵律标签的语言模型，并且输出表示单词假设的可能性的单词假设和第一分数。当假设输入语音的识别结果是单词假设时，词搜索单元（17）还输入元音间隔及其音调标签在输入语音中。音调识别单元（21）基于与从词搜索单元（17）输出的元音间隔相对应的特征量，输出表示从词搜索单元（17）输出的音调标签的可能性的第二分数。再分类单元（22）使用从音调识别单元（21）输出的第二分数来校正从词搜索单元（17）输出的单词假设的第一分数。这样可以提高语调的语音识别精度。

24. 发明申请

US20110196678A1 SPEECH RECOGNITION APPARATUS AND SPEECH RECOGNITION METHOD 有权
标题翻译：语音识别装置和语音识别方法
公开(公告)号：US20110196678A1
公开(公告)日：2011-08-11
申请号：US12672015
申请日：2008-08-22
申请人： Ken Hanazawa
发明人： Ken Hanazawa
IPC分类号： G10L15/04
CPC分类号： G10L15/1807 , G10L15/187 , G10L25/15 , G10L2015/025
摘要： A distance calculation unit (16) obtains the acoustic distance between the feature amount of input speech and each phonetic model. A word search unit (17) performs a word search based on the acoustic distance and a language model including the phoneme and prosodic label of a word, and outputs a word hypothesis and a first score representing the likelihood of the word hypothesis. The word search unit (17) also outputs a vowel interval and its tone label in the input speech, when assuming that the recognition result of the input speech is the word hypothesis. A tone recognition unit (21) outputs a second score representing the likelihood of the tone label output from the word search unit (17) based on a feature amount corresponding to the vowel interval output from the word search unit (17). A rescore unit (22) corrects the first score of the word hypothesis output from the word search unit (17) using the second score output from the tone recognition unit (21). This allows to raise the speech recognition accuracy for tone speech.
摘要翻译：距离计算单元（16）获得输入语音的特征量与每个语音模型之间的声学距离。词搜索单元（17）基于声距进行词搜索和包括单词的音素和韵律标签的语言模型，并且输出表示单词假设的可能性的单词假设和第一分数。当假设输入语音的识别结果是单词假设时，词搜索单元（17）还输入元音间隔及其音调标签在输入语音中。音调识别单元（21）基于与从词搜索单元（17）输出的元音间隔相对应的特征量，输出表示从词搜索单元（17）输出的音调标签的可能性的第二分数。再分类单元（22）使用从音调识别单元（21）输出的第二分数来校正从词搜索单元（17）输出的单词假设的第一分数。这样可以提高语调的语音识别精度。

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