-
公开(公告)号：DE69726235T2
公开(公告)日：2004-08-19
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.
-
公开(公告)号：AU2003253438A1
公开(公告)日：2004-03-11
申请号：AU2003253438
申请日：2003-08-11
Applicant: CANON KK
Inventor： SAKAKIBARA TEIGO , YAMADA MASAYUKI , ERITATE SHINJI , ZHANG ZUYI , KOBAYASHI MOTOKAZU
-
公开(公告)号：DE69905668T2
公开(公告)日：2003-09-25
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：DE69619154D1
公开(公告)日：2002-03-21
申请号：DE69619154
申请日：1996-04-30
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO
Abstract: The method and apparatus performs pattern recognition on given information such as speech data or image data with a reduced amount of calculations of the degree of matching associated with reference patterns. The method and apparatus provides a high speed operation without an increase in the amount of calculations of the degree of matching even when there are a great number of reference patterns. In this invention, the process of calculating the degree of matching includes: a scalar quantization step in which the value of each dimension of an input feature vector is scalar-quantized; a table look-up step in which a table is subjected to a look-up operation on the basis of the quantized value obtained in the scalar quantization step so as to obtain an output value of a reference pattern function for each dimension; and a cumulative matching degree calculation step in which the output value of the reference pattern function obtained in the table loop-up step is accumulated for all dimensions, and the resultant cumulative value is finally employed as the degree of matching between the reference pattern and the input feature vector.
-
公开(公告)号：DE69615288D1
公开(公告)日：2001-10-25
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.
-
Patent Agency Ranking
公开(公告)号：BRPI1107140A2
公开(公告)日：2015-05-12
申请号：BRPI1107140
申请日：2011-09-29
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , SATO MASAYUKI
IPC: G06F17/24 , G06F40/191
Abstract: Aparelho de inserção de caractere, método de controle de um aparelho de inserção de caractere,e, mídia de armazenamento não temporário. É descrito um aparelho de inserção de caractere que torna possível suprimir a degradação da facilidade de uso em um caso em que um usuário visualmente desabilitado insere caracteres usando uma função de autocompletação. No aparelho de inserção de sequência de caractere, uma sequência de caractere a ser inserida como uma parte depois de uma sequência de caractere inserida por um usuário é prevista com base na sequência de caractere inserida pelo, usuário, e a sequência de caractere prevista como uma parte complementar àquela. Em uma modo de guia de voz, informação associada com uma tecla selecionada pelo usuário é lida em voz alta. Quando o modo de guia de voz dor habilitado, o aparelho de inserção de sequência de caractere desabilita a função de autocomplementação e realiza controle, de maneira tal que uma sequência de caractere não possa ser automaticamente completada
-
公开(公告)号：DE60332980D1
公开(公告)日：2010-07-29
申请号：DE60332980
申请日：2003-06-04
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KOMORI YASUHIRO , FUKADA TOSHIAKI
-
公开(公告)号：DE60314929D1
公开(公告)日：2007-08-30
申请号：DE60314929
申请日：2003-02-11
Applicant: CANON KK
Inventor： YAMADA MASAYUKI , KAWASAKI KATSUHIKO , FUKADA TOSHIAKI , OKUTANI YASUO
Abstract: With this invention, an information processing apparatus which has an audio data playback function and text-to-speech synthesis function allows the user to input an instruction by a fewer operations and provides a fast-forward/fast-reverse function optimal to speech synthesis. During speech synthesis, an instruction input by a button operation is supplied to a speech synthesis unit. When playback of audio data is underway, but speech synthesis is inactive, an instruction input by a button operation is supplied to an audio data playback unit. In a fast-forward mode, an abstract is read aloud or head parts of sentences are read aloud. In a fast-reverse mode, head parts of sentences are read aloud. Also, given tones are generated in correspondence with skipped parts.
-
公开(公告)号：DE69917960D1
公开(公告)日：2004-07-22
申请号：DE69917960
申请日：1999-03-05
Applicant: CANON KK
Inventor： YAMADA MASAYUKI
Abstract: A second phoneme is generated in consideration of a phonemic context with respect to a first phoneme as a search target. Phonemic piece data corresponding to the second phoneme is searched out from a database. A third phoneme is generated by changing the phonemic context on the basis of the search result, and phonemic piece data corresponding to the third phoneme is re-searched out from the database. The search or re-search result is registered in a table in correspondence with the second or third phoneme.
-
公开(公告)号：DE69908723T2
公开(公告)日：2004-05-13
申请号：DE69908723
申请日：1999-08-31
Applicant: CANON KK
Inventor： OKUTANI YASUO , YAMADA MASAYUKI
Abstract: A speech synthesizing apparatus for synthesizing a speech waveform stores speech data, which is obtained by adding attribute information onto phoneme data, in a database. In accordance with prescribed retrieval conditions, a phoneme retrieval unit retrieves phoneme data from the speech data that has been stored in the database and retains the retrieved results in a retrieved-result storage area. A processing unit for assigning a power penalty and a processing unit for assigning a phoneme-duration penalty assign the penalties, on the basis of power and phoneme duration constituting the attribute information, to a set of phoneme data stored in the retrieved-result storage area. A processing unit for determining typical phoneme data performs sorting on the basis of the assigned penalties and, based upon the stored results, selects phoneme data to be employed in the synthesis of a speech waveform.
-
-
-
-
-
-
-
-
-
Search Results
42
records
(took 0.036 seconds)
