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. 发明专利

JP2004362419A Information processor and its method 审中-公开
公开(公告)号：JP2004362419A
公开(公告)日：2004-12-24
申请号：JP2003162192
申请日：2003-06-06
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： SAITO NATSUKI , KAMAI TAKAHIRO , YAMAGAMI KATSUYOSHI , KATO YUMIKO , HIROSE YOSHIFUMI
IPC分类号： G06F3/16 , G06F13/00 , G06F17/30
摘要： PROBLEM TO BE SOLVED: To reduce the loads of a user intending to prepare multimedia contents and to easily prepare contents in which voice, an image and a character of a style coincide with each other. SOLUTION: In the case of preparing a mail including multimedia-like contents, a user is allowed to select a character of the mail required to be prepared by the user, voice synthesis parameters (voice data) and picture data matched with the character are sorted so as to be easily selected and presented to the user and the character is allowed to use an individual text input conversion dictionary so that the user can write sentences matched with the character. Consequently, a multimedia mail in which the atmospheres of a text, an image and voice coincide with each other can be perpared. COPYRIGHT: (C)2005,JPO&NCIPI

2. 发明专利

JP2007148039A Speech translation device and speech translation method 有权
标题翻译：语音翻译设备和语音翻译方法
公开(公告)号：JP2007148039A
公开(公告)日：2007-06-14
申请号：JP2005342896
申请日：2005-11-28
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： YAMAGAMI KATSUYOSHI , KATO YUMIKO
IPC分类号： G10L13/08 , G06F17/28 , G10L13/00
摘要： PROBLEM TO BE SOLVED: To provide a speech translation device capable of properly conveying a speaker's emotion and intention contained in the speech of a source language to a listener in the speech of a target language. SOLUTION: The present invention comprises: an input part 101 for acquiring a speech of a source language; a source language table search part 108 for specifying a speaker's emotion and intention of the speech of the source language; a fourth storage part 113 where a target language emotion table 113a is stored; a translation part 109 for generating a plurality of texts of the target language from the acquired speech of the source language; a target language table search part 114 for searching the plurality of texts for a text of which language attribute, and emotion and intention are close to the language attribute vector, and the emotion and intention vector in the target language emotion table 113a, and acquiring an acoustic characteristic vector of the text that has been searched for, from acoustic characteristic vectors in the target language emotion table 113a; a speech synthesis part 115 and an output part 116 for outputting the synthesized speech of the target language of the text. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供一种语音翻译装置，其能够将目标语言的语音中的源语言的语音中包含的说话者的情感和意图恰当地传递给收听者。解决方案：本发明包括：用于获取源语言的语音的输入部分101; 源语言表搜索部分108，用于指定说话者的情感和源语言的语音意图; 存储目标语言情感表113a的第四存储部113; 翻译部分109，用于从所获取的源语言的语音生成目标语言的多个文本; 目标语言表搜索部分114，用于搜索多个文本中的哪个语言属性，情感和意图接近语言属性向量的文本，以及目标语言情绪表113a中的情绪和意图向量，并获取从目标语言情感表113a的声学特征向量中搜索的文本的声学特征向量; 语音合成部分115和输出部分116，用于输出文本的目标语言的合成语音。版权所有（C）2007，JPO＆INPIT

3. 发明专利

JP2003005774A Speech synthesizer 审中-公开
标题翻译：语音合成器
公开(公告)号：JP2003005774A
公开(公告)日：2003-01-08
申请号：JP2001191713
申请日：2001-06-25
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： KATO YUMIKO , YAMAGAMI KATSUYOSHI
IPC分类号： G10L13/06 , G10L13/00 , G10L13/08
摘要： PROBLEM TO BE SOLVED: To enable the meaning of an inputted text to be accurately understood without impairing the naturalness of speech even in the case where the sound speed is largely changed from a standard speed when the inputted text is converted into the speech. SOLUTION: In the case where the speed of the speech inputted by a user is outside a predetermined range, the text to be converted into the speech is converted into a text having a meaning equivalent to the text and having a different expression. The converted text is converted into the speech, outputted and the speed of speech is adjusted by adjusting the amount of information per unit time of the speech.
摘要翻译：要解决的问题：即使在输入的文本被转换成语音时，在声速从标准速度发生很大变化的情况下，也能够准确地理解输入的文本的含义而不损害语音的自然性。解决方案：在由用户输入的语音速度超出预定范围的情况下，要转换成语音的文本被转换成具有与文本相同的含义并具有不同表达的文本。转换的文本被转换成语音，输出，并通过调整语音单位时间的信息量来调整语速。

4. 发明专利

JP2004246227A Text speech synthesis system and method 审中-公开
公开(公告)号：JP2004246227A
公开(公告)日：2004-09-02
申请号：JP2003037795
申请日：2003-02-17
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： YAMAGAMI KATSUYOSHI , HIROSE YOSHIFUMI , KATO YUMIKO , KAMAI TAKAHIRO
IPC分类号： G10L13/06 , G10L13/00 , G10L13/08
摘要： PROBLEM TO BE SOLVED: To solve problems of ambiguity in morpheme analysis (ambiguity of division into words and ambiguity of a reading of an identical-notation word).
SOLUTION: A word dictionary 220 on a speech synthesis side 200 includes at least the vocabulary of a word dictionary 150 on a KANA(Japanese syllable)-to-KANJI(Chinese character) conversion side 100. Identifies (word ID) are assigned to registered vocabularies of both the dictionaries 150 and 220. The same word ID is assigned to identical words in the both 150 and 220. A word is determined through KANA-KANJI conversion on the KANA-KANJI conversion side 100 and then the word ID of the determined word is obtained. The obtained word ID is sent to the speech synthesis side 200. The speech synthesis side 200 performs retrieval from the dictionary 200 by using the word ID to obtain language information (notation, pronunciation, accent, part of speech, and accent combination information) on the word corresponding to the word ID.
COPYRIGHT: (C)2004,JPO&NCIPI

5. 发明专利

JP2004102242A Voice synthesizing device 有权
公开(公告)号：JP2004102242A
公开(公告)日：2004-04-02
申请号：JP2003191289
申请日：2003-07-03
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： HIROSE YOSHIFUMI , YAMAGAMI KATSUYOSHI , WAKITA YUMI
IPC分类号： G10L13/08 , G10L13/00
摘要： PROBLEM TO BE SOLVED: To provide a device and a method for voice synthesis that can represent a compound word with sufficient precision.
SOLUTION: A compound word extraction part 12 extracts a compound word (a word string constituting the compound word) from text information divided into words. A meaning imparting part 13 picks up meaning information on the words constituting the compound word from a thesaurus dictionary part 18 to generate compound word meaning information and imparts it to the extracted compound word. A rule application part 14 while referring to a separation rule stored in a separation rule dictionary part 19 determines a position where the compound word is separated according to the compound word meaning information imparted to the compound word. A rhythm generation part 15 generates rhythm of the text information according to the determined separation position. A voice synthesis part 16 generates a synthesized voice of the text information according to the generated rhythm.
COPYRIGHT: (C)2004,JPO

6. 发明专利

JP2006171399A Data input device 审中-公开
标题翻译：数据输入设备
公开(公告)号：JP2006171399A
公开(公告)日：2006-06-29
申请号：JP2004364218
申请日：2004-12-16
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： HIROSE YOSHIFUMI , NISHIZAKI MAKOTO , KATO YUMIKO , YAMAGAMI KATSUYOSHI , OONO TAKEO
IPC分类号： G10L13/00 , G10L13/02 , G10L15/22 , G10L21/02 , G10L21/04
摘要： PROBLEM TO BE SOLVED: To provide a voice-interactive device capable of presenting the degree of the progress rate of an interaction to a user without interrupting the interaction, even when input/output information is limited to sound. SOLUTION: The voice-interactive device which inputs data to respective slots of a task frame, consisting of a plurality of slots is equipped with an input section 101 which inputs data from the user to respective slot, an interaction management section 103 which calculates the degree of progress of data input to the plurality of slots of the task frame; a sound information DB 105 which stores sound information corresponding to the task frame, an output sound generation section 106 which changes or selects the sound information according to the degree of progress; a sound output section 104 which requests the user to input data of the respective slots; and a sound output section 107 which reproduces and outputs the changed or selected sound information, simultaneously with the input requesting for data by the sound output section 104. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：即使当输入/输出信息被限制为声音时，提供能够向用户呈现交互进度的程度而不中断交互的语音交互设备。解决方案：将数据输入到由多个时隙组成的任务帧的相应时隙的语音交互设备配备有从用户向相应时隙输入数据的输入部分101，交互管理部分103 计算输入到任务帧的多个时隙的数据的进度; 存储与任务帧对应的声音信息的声音信息DB105，根据进度而改变或选择声音信息的输出声音生成部106; 声音输出部104，其请求用户输入各个时隙的数据; 以及声音输出部107，其与通过声音输出部104请求数据的输入同时再现并输出改变或选择的声音信息。（C）2006年，JPO＆NCIPI

7. 发明专利

JP2007183421A Speech synthesizer apparatus 审中-公开
标题翻译：语音合成器装置
公开(公告)号：JP2007183421A
公开(公告)日：2007-07-19
申请号：JP2006001631
申请日：2006-01-06
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： KATO YUMIKO , YAMAGAMI KATSUYOSHI
IPC分类号： G10L13/08
摘要： PROBLEM TO BE SOLVED: To provide a speech synthesizer apparatus in which mutual relevancy of language attributes of synthesized speech, acoustic characteristics of synthesized speech, and feeling which a user desires to express by the whole synthesized speech, is appropriately kept. SOLUTION: The speech synthesizer apparatus comprises: a feeling data base 306 which has a plurality of feeling expressing patterns composed of a language attribute vector, an acoustic attribute vector, and a feeling vector for indicating the feeling expressed by those; a text input section 301 for generating the language attribute vector which indicates the language attribute of a text; a language analysis section 304; a language attribute analysis section 305; a feeling input section 302 for obtaining the feeling vector which indicates the feeling; a pattern search section 307a for searching and extracting the feeling expressing pattern having a content close to the language attribute vector of the text and the feeling vector which is obtained by the feeling input section 302, from the feeling data base 306; and a speech synthesizing section 309 for performing speech synthesizing on the text, based on the acoustic attribute vector included in the extracted feeling expressing pattern. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供一种语音合成装置，其中适当地保持合成语音的语言属性，合成语音的声学特性和用户期望通过整个合成语音表达的感觉的相互关系。语音合成器装置包括：感觉数据库306，其具有由语言属性向量，声学属性向量和用于指示由它们表达的感觉的感觉向量组成的多种感觉表达模式; 用于生成指示文本的语言属性的语言属性向量的文本输入部分301; 语言分析部304; 语言属性分析部305; 用于获得表示感觉的感觉向量的感觉输入部302; 用于从感觉数据库306中搜索和提取具有接近文本的语言属性向量的内容的感觉表达模式和由感觉输入部分302获得的感觉向量的模式搜索部分307a; 以及语音合成部分309，用于基于包括在所提取的感觉表达模式中的声学属性矢量，对文本进行语音合成。版权所有（C）2007，JPO＆INPIT

8. 发明专利

JP2006164172A Information presentation device and information presentation method 审中-公开
标题翻译：信息呈现装置和信息呈现方法
公开(公告)号：JP2006164172A
公开(公告)日：2006-06-22
申请号：JP2004358548
申请日：2004-12-10
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： NISHIZAKI MAKOTO , HIROSE YOSHIFUMI , YAMAGAMI KATSUYOSHI , OONO TAKEO
IPC分类号： G06F3/16 , G06F3/01
摘要： PROBLEM TO BE SOLVED: To provide an information presentation device capable of efficiently and compactly transmitting information by making use of a plurality of modal expressions. SOLUTION: The information presentation device which presents information in a plurality of modal expressions comprises: a text input part 101 for accepting text input; a text analysis part 102 for breaking down the text into a plurality of elements by analyzing the structure of the inputted text; a text element classification part 103 for determining a modal expression in which each element broken down should be outputted; a voice selection part 104 for presenting the content of the text by outputting the elements constituting the text in a plurality of modal expressions according to the determination by the text element classification part 103; a text generation part 105; a voice output part 106; and a voice synthesis part 107. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供能够通过利用多个模态表达来有效且紧凑地发送信息的信息呈现装置。解决方案：以多个模态表达式呈现信息的信息呈现装置包括：用于接受文本输入的文本输入部分101; 文本分析部分102，用于通过分析输入的文本的结构来将文本分解成多个元素; 用于确定应该输出每个元素分解的模态表达式的文本元素分类部分103; 声音选择部分104，用于根据文本元素分类部分103的确定，通过以多个模态表达形式输出构成文本的元素来呈现文本的内容; 文本生成部105; 语音输出部106; 和语音合成部分107.版权所有（C）2006，JPO＆NCIPI

9. 发明专利

JP2004341259A Speech segment expanding and contracting device and its method 审中-公开
标题翻译：语音段扩展和承包设备及其方法
公开(公告)号：JP2004341259A
公开(公告)日：2004-12-02
申请号：JP2003137957
申请日：2003-05-15
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： KATO YUMIKO , KAMAI TAKAHIRO , YAMAGAMI KATSUYOSHI , HIROSE YOSHIFUMI , SAITO NATSUKI
IPC分类号： G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a speech synthesis system which exhibits small speech quality deterioration and is capable of adjusting the continuance length of a speech segment according to a variety of speaking states.
SOLUTION: A speech synthesis system 10 expands or contracts the temporal length of speech segments for speech synthesis and is equipped with: a robustness calculation part 150 which calculates robustness for the time length expansion or contraction of speech segment data by the states of sound models corresponding to respective speech segments by using a speech segment database 110a including border information on the speech segments and a sound model database 130 using a statistical method having a plurality of states for each speech segments; and a frame time length expansion/contraction rate calculation part 200 which expands or contracts the temporal length of each part of the speech segment corresponding to each state for the speech segments for speech synthesis, etc., on the basis of the ratio of the robustness of the individual calculated states.
COPYRIGHT: (C)2005,JPO&NCIPI
摘要翻译：要解决的问题：提供表现出小的语音质量劣化并且能够根据各种说话状态来调整语音段的连续长度的语音合成系统。解决方案：语音合成系统10扩展或收缩用于语音合成的语音段的时间长度，并且配备有：鲁棒性计算部分150，其计算语音段数据的时间长度扩展或收缩的鲁棒性，通过使用包括语音段的边界信息的语音段数据库110a和使用对于每个语音段具有多个状态的统计方法的声音模型数据库130，对应于各个语音段的声音模型; 以及帧时间长度扩展/收缩率计算部分200，其基于鲁棒性的比率来扩展或收缩对应于用于语音合成的语音段的每个状态的语音段的每个部分的时间长度等的个人计算状态。版权所有（C）2005，JPO＆NCIPI

10. 发明专利

JP2004240201A Speech synthesizer 有权
公开(公告)号：JP2004240201A
公开(公告)日：2004-08-26
申请号：JP2003029682
申请日：2003-02-06
申请人： Matsushita Electric Ind Co Ltd , 松下電器産業株式会社
发明人： YAMAGAMI KATSUYOSHI , KATO YUMIKO , MOCHIZUKI AKIRA
IPC分类号： G10L13/08 , G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a speech synthesizer which is capable of synthesizing read aloud speech of consistently high quality by utilizing the rhythm pattern data formed from actual speech to the maximum possible extent.
SOLUTION: A language analysis section 101 which performs analysis of input text and outputs the result of language processing expressed by a phonetic symbol sequence assigns the position where the phonetic symbol sequence is divided in the arbitrary accent phrase of the phonetic symbol sequence and a rhythm retrieval section 102 carries out retrieval in an accent phrase unit or the unit segmented by the accent division position assigned within the accent phrase as the unit for retrieving the rhythm pattern from a rhythm pattern data base 103, thereby carrying out rhythm formation without using means exclusive of the rhythm pattern retrieval.
COPYRIGHT: (C)2004,JPO&NCIPI

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