-
公开(公告)号：DE69908518T2
公开(公告)日：2004-05-06
申请号：DE69908518
申请日：1999-08-31
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO , OHTSUKA MITSURU
Abstract: An amplitude altering magnification (r) applied to sub-phoneme units of a voiced portion and an amplitude altering magnification s to be applied to sub-phoneme units of an unvoiced portion are determined based upon a target phoneme average power (p0) of synthesized speech and power (p) of a selected phoneme unit. Sub-phoneme units are extracted from a phoneme to be synthesized. From among the extracted sub-phoneme units, a sub-phoneme unit of the voiced portion is multiplied by the amplitude altering magnification (r), and a sub-phoneme unit of the unvoiced portion is multiplied by the amplitude altering magnification (s). Synthesized speech is obtained using the sub-phoneme units thus obtained. This makes it possible to realize power control in which any decline in the quality of synthesized speech is reduced.
-
公开(公告)号：DE69908518D1
公开(公告)日：2003-07-10
申请号：DE69908518
申请日：1999-08-31
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO , OHTSUKA MITSURU
Abstract: An amplitude altering magnification (r) applied to sub-phoneme units of a voiced portion and an amplitude altering magnification s to be applied to sub-phoneme units of an unvoiced portion are determined based upon a target phoneme average power (p0) of synthesized speech and power (p) of a selected phoneme unit. Sub-phoneme units are extracted from a phoneme to be synthesized. From among the extracted sub-phoneme units, a sub-phoneme unit of the voiced portion is multiplied by the amplitude altering magnification (r), and a sub-phoneme unit of the unvoiced portion is multiplied by the amplitude altering magnification (s). Synthesized speech is obtained using the sub-phoneme units thus obtained. This makes it possible to realize power control in which any decline in the quality of synthesized speech is reduced.
-
公开(公告)号：DE69615288T2
公开(公告)日：2002-06-27
申请号：DE69615288
申请日：1996-06-20
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO
Abstract: With respect to pattern recognition or the like, this invention is aimed at reducing the arithmetic processing steps of determining analogy between an inputted pattern and reference patterns in order to enhance the speed of the recognition process. At first, a quantization code book is designed to prepare a single-output table and a mixture-output table. Then, referring to these tables, single-output data and mixture-output data are worked out from an inputted pattern. In accordance with these data thus worked out, the adaptability between the inputted pattern and reference patterns is calculated in order to obtain the analogy between them.
-
公开(公告)号：AU2003274733A1
公开(公告)日：2004-05-04
申请号：AU2003274733
申请日：2003-10-15
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , ERITATE SHINJI , KOBAYASHI MOTOKAZU , SAKAKIBARA TEIGO
Abstract: In a manufacturing process for a fuel cell having a fuel electrode, an oxidizer electrode, and a polymer electrolyte membrane held between both the electrodes, and having electrode catalyst layers which are individually provided between both the electrodes and the polymer electrolyte membrane, the process has the step of ejecting an electrode catalyst composition containing conductive particles carrying thereon at least a catalyst, by an ink-jet process to form the electrode catalyst layers. This provides a fuel cell manufacturing process which can accurately control the coverage of catalyst layers and also can simply provide pores while controlling the same.
-
公开(公告)号：DE69726235D1
公开(公告)日：2003-12-24
申请号：DE69726235
申请日：1997-09-18
Applicant: CANON KK
Inventor： KOMORI YASUHIRO , KOSAKA TETSUO , YAMADA MASAYUKI
Abstract: The present invention aims to provide a high-speed speech recognition method of a high recognition rate, utilizing speaker models. For this purpose, the method of this invention executes an acoustic process on the input speech, then calculates a coarse output probability utilizing an unspecified speaker model, and calculates a fine output probability utilizing an unspecified speaker model and clustered speaker models, for the states estimated, by the result of coarse calculation, to contribute to the result of recognition. Candidates of recognition are extracted by a common language search based on the obtained result, and a fine language search is conducted on thus extracted candidates to determine the result of recognition.
-
Patent Agency Ranking
公开(公告)号：DE69905668D1
公开(公告)日：2003-04-10
申请号：DE69905668
申请日：1999-09-16
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO , NAKAGAWA KENICHIRO
Abstract: A central processing unit determines whether speech separately uttered as a single syllable is included in input speech. On the basis of the determination result, an output unit is used to notify the user of information prompting the user to input speech again.
-
公开(公告)号：DE69519840T2
公开(公告)日：2001-06-28
申请号：DE69519840
申请日：1995-09-29
Applicant: CANON KK
Inventor： KOMORI YASUHIRO , OHORA YASUNORI , YAMADA MASAYUKI
Abstract: A speech recognition method uses continuous mixture Hidden Markov Models (HMM) for probability processing including a first type of HMM having a small number of mixtures and a second type of HMM having a larger number of mixtures. First output probabilities are formed for inputted speech using the small number of mixtures type HMM and second output probabilities are formed for the input speech using the large number of mixtures type HMM for selected states corresponding to the highest output probabilities of the first type HMM. The input speech is recognized from both the first and second output probabilities.
-
公开(公告)号：DE69519840D1
公开(公告)日：2001-02-15
申请号：DE69519840
申请日：1995-09-29
Applicant: CANON KK
Inventor： KOMORI YASUHIRO , OHORA YASUNORI , YAMADA MASAYUKI
Abstract: A speech recognition method uses continuous mixture Hidden Markov Models (HMM) for probability processing including a first type of HMM having a small number of mixtures and a second type of HMM having a larger number of mixtures. First output probabilities are formed for inputted speech using the small number of mixtures type HMM and second output probabilities are formed for the input speech using the large number of mixtures type HMM for selected states corresponding to the highest output probabilities of the first type HMM. The input speech is recognized from both the first and second output probabilities.
-
公开(公告)号：DE69421324D1
公开(公告)日：1999-12-02
申请号：DE69421324
申请日：1994-06-15
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , OHORA YASUNORI , KOMORI YASUHIRO
IPC: G10L15/10 , G10L15/00 , G10L15/06 , G10L15/18 , G10L15/22 , G10L15/26 , G10L15/28 , G10L5/06 , G10L7/08 , G10L9/06
Abstract: The invention relates to voice communication method and apparatus and it is an object that when the acceptable vocabulary or grammar is dynamically changed in accordance with a communication state, a troublesomeness for allowing the user to again utter a speech which does not correspond to the predicted vocabulary and which cannot be acceptable is eliminated. For the above purpose, the speech which cannot be perceived is handled as an unknown word, a question to induce an answer such that the unknown word becomes included the acceptable vocabulary is performed, and the unknown word portion is reevaluated at a time point when the unknown word becomes included the acceptable vocabulary due to the induced answer. Thus, the user does not need to again utter the same answer.
-
30.发明专利
公开(公告)号：DE602005022006D1
公开(公告)日：2010-08-12
申请号：DE602005022006
申请日：2005-02-22
Applicant: CANON KK , UNIV OSAKA PREFECTURE
Inventor： KOTANI YOSHINORI , YAMADA MASAYUKI , KUBOTA MAKOTO , ZHANG ZUYI , TATSUMISAGO MASAHIRO , TADANAGA KIYOHARU , MINAMI TSUTOMU , MATSUDA ATSUNORI
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.03 seconds)
