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

JP2003177773A SPEECH SYNTHESIZER AND ITS METHOD 审中-公开
公开(公告)号：JP2003177773A
公开(公告)日：2003-06-27
申请号：JP2002335330
申请日：2002-11-19
申请人： ARCADIA KK
发明人： AMASHIRO SEIICHI , HIRAI TOSHIO
IPC分类号： G10L13/04
摘要： PROBLEM TO BE SOLVED: To provide a speech processor which changes audio intensity, pitch frequency, or utterance time length by a simple operation. SOLUTION: When an operation icon 200 (an upward arrow) is clicked, a correction is made so as to increase the audio intensity and the audio pitch frequency on the whole. When an operation icon 204 (a downward arrow) is clicked, a correction is made so as to decrease the audio intensity and the audio pitch frequency on the whole. When an operation icon 206 (a leftward arrow) is clicked, the correction is made so as to shorten the utterance voice length by, for example, deleting several pitches. When an operation icon 202 (a rightward arrow) is clicked, a correction is made so as to lengthen the utterance voice length by, for example, overlapping several pitches. COPYRIGHT: (C)2003,JPO

2. 发明专利

JP2001109500A VOICE SYNTHESIS DEVICE AND VOICE SYNTHESIS METHOD 失效
公开(公告)号：JP2001109500A
公开(公告)日：2001-04-20
申请号：JP28512599
申请日：1999-10-06
申请人： ARCADIA KK
发明人： AMASHIRO SEIICHI , HIRAI TOSHIO
IPC分类号： G10L21/04 , G01L13/00 , G01L13/04 , G10L13/02 , G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a pitch change processing technology which causes less damage to the naturalness of voice. SOLUTION: A waveform in the respective pitches of a voice waveform is divided into 1) time α when a minus peak attended with the close of vocal cords appears, 2) a section β where the waveform based on the shape of a vocal tract started from the minus peak appears 3) a section γ where the voice waveform bases on the shape of the vocal tract is converted toward the next minus peak while it is attenuated. Processing of waveform for changing the pitch is executed in a part where the influence of the minus peak attended with the close of the vocal cords is small (namely, the section γ just before the next minus peak) based on the above characteristic of the voice waveform. Thus, the processing can be executed while the shape of the waveform near the peak is completely maintained and the influence of the pitch change is suppressed to be minimum.

3. 发明专利

JP2004021810A Recommendation system using statistical inference system 审中-公开
公开(公告)号：JP2004021810A
公开(公告)日：2004-01-22
申请号：JP2002178523
申请日：2002-06-19
申请人： Asset Arcadia Kk , アセットアルカディア株式会社
发明人： YOSHINARI HIROAKI
IPC分类号： G06Q10/00 , G06Q30/02 , G06Q30/06 , G06Q50/00 , G06Q50/10 , G06F17/60
摘要： PROBLEM TO BE SOLVED: To provide a recommendation system using a statistical inference system capable of distributing effective contents accurately reflecting customer's interests and liking on the basis of highly accurate inference without requiring enormous labor for data collection for initialization and operation for relating commodities. SOLUTION: The recommendation system is provided with a Web access analyzer 10, a mail click analyzer 20 and a statistical inference device 30 for storing many liking information obtained from these analyzers 10, 20 and statistically inferring the inclination of liking. Liking data inferred from the liking inclination of each customer by the inference device 30 are fed back to the analyzers 10, 20. Then contents suited to the liking of each customer are distributed by an Internet shopping site or an advertisement mail. COPYRIGHT: (C)2004,JPO

4. 发明专利

JP2003091601A DATA PROCESSING SYSTEM AND METHOD 审中-公开
公开(公告)号：JP2003091601A
公开(公告)日：2003-03-28
申请号：JP2001281495
申请日：2001-09-17
申请人： ARCADIA KK
发明人： AMASHIRO SEIICHI , SHIRAHAMA NAGAHISA , MORIYAMA TAKAAKI
IPC分类号： G06Q50/10 , G06Q50/00 , G06F17/60
摘要： PROBLEM TO BE SOLVED: To realize a system for correcting the data without changing the essential contents indicated by the data and the data format with respect to the data prepared by a user side, and providing the corrected data. SOLUTION: A user terminal 20 transmits the user information and the voice data to a server computer 10. The server computer 10 performs the noise eliminating process by a computer and manual operation for the first 20 seconds of the voice data. The voice data after the noise elimination is transmitted to the user terminal 20. A user previews each voice, and finally decides the kind of service (computer or manual operation). The server computer 10 performs the noise eliminating process by a method designated by the user, and returns the voice data to the user terminal 10.

5. 发明专利

JP2002140243A NETWORK SYSTEM FOR PROCESSING MANAGEMENT DEVICE 失效
公开(公告)号：JP2002140243A
公开(公告)日：2002-05-17
申请号：JP2000332945
申请日：2000-10-31
申请人： ARCADIA KK
发明人： FUKUROTANI TAKEO , AMASHIRO SEIICHI
IPC分类号： G06F3/16 , G06F13/00 , G06F15/00 , G10L13/00 , G10L15/00 , G10L15/22 , G10L15/28
摘要： PROBLEM TO BE SOLVED: To provide a network system for achieving a processing device which is as if completely automated. SOLUTION: When personal information is inputted in voice by a user, an automatic audio response unit 31 records the voice to prepare a recorded voice file, and conducts a processing to convert the voice to character information (voice recognition processing). When the voice recognition processing is failed, a SOHO bulletin board managed by a SOHO management server 11 is connected, and an appropriate SOHO operator 211 is selected to send a mail attaching the recorded voice file to a SOHO terminal 211. The voice in the recorded voice file is intended for conversion to the character information by the SOHO operator 211. The SOHO operator 211 hears the voice in the recorded voice file, and sends a mail to the automatic audio response unit 31 as the character information. The automatic audio response unit 31 registers it on a database.

6. 发明专利

JP2002032366A MORPHEME ANALYSIS SYSTEM AND MORPHEME ANALYSIS METHOD 失效
公开(公告)号：JP2002032366A
公开(公告)日：2002-01-31
申请号：JP2001114935
申请日：2001-04-13
申请人： ARCADIA KK
发明人： AMASHIRO SEIICHI
IPC分类号： G06F17/27
摘要： PROBLEM TO BE SOLVED: To provide a morpheme analysis system and a morpheme analysis method, capable of accurately and quickly performing a morpheme analysis. SOLUTION: When a morpheme follows another optional character string and is combined with the character string, the morpheme turns into two or more morphemes that are sectioned in the character string of the morpheme, the information of the sectioned position is also recorded in a Kanji (Chinese character) character string morpheme N character registration dictionary 12 to be made correspond to the morpheme. A kanji character string morpheme analysis program 14 acquires a 1st morpheme candidate by a longest match principle, and tries to re-acquire a 2nd morpheme candidate by the longest match principle from the sectioned position when the sectioned position information is recorded in the 1st morpheme candidate. A plurality of Hiragana (Japanese syllabary) morphemes obtained by being connected, while taking grammatical connection correctness into consideration are preliminarily recorded in a Hiragana morpheme connection list dictionary 18. A Hiragana character string morpheme analysis program 16 acquires a morpheme to be collated with the dictionary 18 with character string data.

7. 发明专利

JP2003216186A SPEECH DATA DISTRIBUTION MANAGEMENT SYSTEM AND ITS METHOD 审中-公开
公开(公告)号：JP2003216186A
公开(公告)日：2003-07-30
申请号：JP2002011325
申请日：2002-01-21
申请人： ARCADIA KK
发明人： AMASHIRO SEIICHI
IPC分类号： G06F3/16 , G06F21/10 , G06Q50/00 , G06Q50/10 , G10L13/02 , G10L13/04 , G10L13/06 , G10L19/00 , G06F17/60 , G10L13/08
摘要： PROBLEM TO BE SOLVED: To realize a speech data distribution management system for promoting use of phonemic data while protecting rights of human voices by unitarily managing the phonemic data regarding a plurality of human voices. SOLUTION: A user terminal 14 transmits distribution request application of incoming voice to a service presentation server 10. The distribution request application contains desired personal information and the speech contents. The service presentation server 10 transmits the personal information, the voice contents, etc., to a speech management server 12. The speech management server 12 unitarily manages speech parameters regarding a plurality of persons and generates and outputs speech data from the speech parameter of the applicable person. A user receives the speech data as the incoming voice and reproduces it by a cellular telephone, etc. COPYRIGHT: (C)2003,JPO

8. 发明专利

JP2002185618A ADVERTISING DEVICE 失效
公开(公告)号：JP2002185618A
公开(公告)日：2002-06-28
申请号：JP2000381103
申请日：2000-12-14
申请人： ARCADIA KK
发明人： SHIRAHAMA NAGAHISA , ABE YASUSHI , AMASHIRO SEIICHI
IPC分类号： G06Q10/00 , G06Q30/02 , G06Q30/04 , G06Q30/06 , G06Q50/00 , G09F25/00 , G10L13/00 , G10L13/04 , G10L15/00 , G10L15/22 , H04M3/42 , H04M11/00 , H04M15/00 , G06F17/60 , G10L15/28
摘要： PROBLEM TO BE SOLVED: To provide an advertising device capable of realizing high advertising efficiency by allowing a user to positively participate in advertisements. SOLUTION: A user A of a portable telephone 150 calls an advertising device 100. At that time, a question related with an enterprise X being an advertiser is presented from the advertising device 100 to the user A (A coffee associates XX) (2). Then, the user A pronounces the answer to the question through the portable telephone 150 (3). At the time of receiving the answer from the user A, the advertising device 100 extracts the answer by voice recognition processing, and judges whether or not the extracted answer is correct. When the answer is correct, the user A is given a right to talk free for a prescribed call tariff (4). The user A is allowed to call the other party the user himself wants to call through a telephone company W (5).

9. 发明专利

JP2002140190A SPEECH RECOGNITION PROCESSOR 失效
公开(公告)号：JP2002140190A
公开(公告)日：2002-05-17
申请号：JP2000332912
申请日：2000-10-31
申请人： ARCADIA KK
发明人： SOBASHIMA YASUO , FUJII YASUHIRO , AMASHIRO SEIICHI
IPC分类号： G06F3/16 , G06F3/00 , G06F3/01 , G10L15/00 , G10L15/22 , G10L15/28
摘要： PROBLEM TO BE SOLVED: To provide a speech recognition processor allowing a voice input for speech recognition at a natural timing with an easy operation. SOLUTION: A user inputs a position for displaying an image on a display part 2 by operating a position input part 4. In conformation to this operation, a speech recognition part 8 starts the read of speech from a speech input part 6. The user inputs an image to be displayed by speech through the speech input part 6. When the speech input is finished, the user operates the position input part 4. The speech recognition part 8 ends the read of voice in response to this operation. A processing execution part 10 reads the display image corresponding to the recognition result in response to the recognition result of the recognition part 8, and enlarges or contracts the image so as to be matched to the size of a guide image. Thereafter, the display image matched to the size of the guide image is displayed in the position on the display part 2 designated by the position input part 4.

10. 发明专利

JP2001100776A VOCIE SYNTHESIZER 失效
公开(公告)号：JP2001100776A
公开(公告)日：2001-04-13
申请号：JP28052899
申请日：1999-09-30
申请人： ARCADIA KK
发明人： ASHIMURA KAZUYUKI , AMASHIRO SEIICHI
IPC分类号： G10L13/06 , G10L13/02 , G10L13/08
摘要： PROBLEM TO BE SOLVED: To provide a voice synthesizer improved by realizing quickness of processing as well as naturalness of an output voice. SOLUTION: A waveform candidate acquisition means 8 divides given phonemic information into extended syllables and acquires corresponding sample voice waveform data from a voice database 6. Since many sample waveform data are stored in the voice database 6, plural sample voice waveform data are obtained as candidates for one extended syllable. A waveform candidate determination means 10 determines one sample voice waveform data out of plural sample voice waveform data, which are acquired by the waveform candidate acquisition means 8, for one extended syllable in consideration of context or the like. A waveform coupling means 12 couples a series of sample voice waveform data obtained by the waveform candidate determination means 10 to obtain voice waveform data to be outputted. An analog conversion means 4 converts it to an analog voice signal.

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