Image processing apparatus, speech recognition processing apparatus, control method for speech recognition processing apparatus, and computer-readable storage medium for computer program

• US 8,630,852 B2
• Filed: 09/16/2010
• Issued: 01/14/2014
• Est. Priority Date: 09/18/2009
• Status: Active Grant

• Current Assignee: Konica Minolta Business Technologies Incorporated (Konica Minolta Inc.)
• Original Assignee: Konica Minolta Business Technologies Incorporated (Konica Minolta Inc.)
• Inventors: Itoh, Ayumi
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US12/883,388
• Publication Number:
  US 20110071829A1
• Time in Patent Office: 1,216 Days
• Field of Search: 704231-257
• US Class Current: 704/243
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

An image processing apparatus includes a speech input portion that receives an input of speech from a user, a dictionary storage portion that stores a dictionary configured by phrase information pieces for recognizing the speech, a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders, a compound phrase registration portion that registers the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces, a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase.

Claims

1. An image processing apparatus provided with an image reading apparatus that reads an image of an original, the image processing apparatus comprising:

a speech input portion that receives an input of speech from a user;

a dictionary storage portion that stores a dictionary configured by phrase information pieces for recognizing the speech;

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces;

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

an image processing portion that executes processing on the image based on a result of the speech recognition performed by the speech recognition portion;

an associated information storage portion that stores associated information pieces that are associated with the compound phrases;

a function phrase storage portion that stores a function phrase that is related to a function that the image processing apparatus has;

a user phrase writing portion that writes a user phrase designated by the user to the associated information storage portion; and

a processor to control one or more of the portions;

wherein the image processing portion extracts an associated information piece among the associated information pieces stored in the associated information storage portion based on the result of the speech recognition performed by the speech recognition portion, and executes processing on the image with use of the extracted associated information piece; and

wherein the compound phrase generation portion generates the compound phrases with use of the function phrase and the user phrase.

2. The image processing apparatus according to claim 1,

wherein a plurality of dictionaries are provided in association with a plurality of operation screens prepared for display on a display apparatus, and

the speech recognition portion performs speech recognition on the speech with use of the dictionary that corresponds to the operation screen displayed on the display apparatus at the time the speech was input.

3. The image processing apparatus according to claim 1,

wherein in a case where the user phrase designated by the user has already been written to the associated information storage portion, a warning is displayed to the user on the display apparatus.

4. An image processing apparatus provided with an image reading apparatus that reads an image of an original, the image processing apparatus comprising:

a speech input portion that receives an input of speech from a user;

a dictionary storage portion that stores a dictionary configured by phrase information pieces for recognizing the speech;

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces;

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

an image processing portion that executes processing on the image based on a result of the speech recognition performed by the speech recognition portion; and

a processor to control one or more of the portions;

wherein the compound phrase generation portion generates the plurality of compound phrases formed by the combinations to which a predetermined particle and a predetermined verb have been added such that the compound phrases are sentences.

5. A speech recognition processing apparatus for performing speech recognition on speech, comprising:

a speech input portion that receives an input of speech from a user;

a dictionary storage portion that stores a dictionary configured by phrase information pieces for recognizing the speech;

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces;

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

an associated information storage portion that stores associated information pieces that are associated with the compound phrases,

an image processing portion that extracts an associated information piece among the associated information pieces stored in the associated information storage portion based on a result of the speech recognition performed by the speech recognition portion, and executes processing on the image with use of the extracted associated information piece

a function phrase storage portion that stores a function phrase that is related to a function that the image processing apparatus has;

a user phrase writing portion that writes a user phrase designated by the user to the associated information storage portion; and

a processor to control one or more of the portions;

wherein the compound phrase generation portion generates the compound phrases with use of the function phrase and the user phrase.

6. A control method for using a processor to control a speech recognition processing apparatus to perform speech recognition, the method comprising the steps of:

storing, in the speech recognition processing apparatus, a dictionary configured by phrase information pieces for recognizing speech;

generating a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

storing in an associated information storage portion associated information pieces that are associated with the compound phrases;

registering the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces;

performing by a speech recognition portion, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

extracting an associated information piece among the associated information pieces stored in the associated information storage portion based on the result of the speech recognition performed by the speech recognition portion;

using an image processing portion to execute processing on an image with use of the extracted associated information piece;

storing a function phrase that is related to a function that the image processing portion has; and

writing a user phrase designated by the user to the associated information storage portion,

wherein the compound phrase generation portion generates the compound phrases with use of the function phrase and the user phrase.

7. A non-transitory computer readable storage medium for storing a computer program for causing a computer to control a speech recognition processing apparatus for performing speech recognition, when executed by the computer, the computer program causing the speech recognition processing apparatus to realize:

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in a dictionary as phrase information pieces for recognizing speech; and

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

an associated information storage portion that stores associated information pieces that are associated with the compound phrases,

a function phrase storage portion that stores a function phrase that is related to a function that the image processing apparatus has; and

a user phrase writing portion that writes a user phrase designated by the user to the associated information storage portion;

wherein the image processing portion extracts an associated information piece among the associated information pieces stored in the associated information storage portion based on the result of the speech recognition performed by the speech recognition portion, and executes processing on the image with use of the extracted associated information piece; and

wherein the compound phrase generation portion generates the compound phrases with use of the function phrase and the user phrase.

8. A speech recognition processing apparatus for performing speech recognition on speech, comprising:

a speech input portion that receives an input of speech from a user;

a dictionary storage portion that stores a dictionary configured by phrase information pieces for recognizing the speech;

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces;

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase; and

a processor for controlling one or more of the portions;

wherein the compound phrase generation portion generates the plurality of compound phrases formed by the combinations to which a predetermined particle and a predetermined verb have been added such that the compound phrases are sentences.

9. A control method for using a processor to control a speech recognition processing apparatus to perform speech recognition, comprising the steps of:

storing, in the speech recognition processing apparatus, a dictionary configured by phrase information pieces for recognizing speech;

using a compound phrase generation portion to generate a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

registering the plurality of compound phrases that have been generated in the dictionary as the phrase information pieces; and

performing, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

wherein the compound phrase generation portion generates the plurality of compound phrases formed by the combinations to which a predetermined particle and a predetermined verb have been added such that the compound phrases are sentences.

10. A non-transitory computer readable storage medium for storing a computer program for causing a computer to control a speech recognition processing apparatus for performing speech recognition, when executed by the computer, the computer program causing the speech recognition processing apparatus to realize:

a compound phrase generation portion that generates a plurality of compound phrases formed by all combinations of a plurality of predetermined phrases in different orders;

a compound phrase registration portion that registers the plurality of compound phrases that have been generated in a dictionary as phrase information pieces for recognizing speech; and

a speech recognition portion that, in a case where speech including a speech phrase formed by the plurality of predetermined phrases said in an arbitrary order has been input, performs speech recognition on the speech by searching the dictionary for a compound phrase that matches the speech phrase;

wherein the compound phrase generation portion generates the plurality of compound phrases formed by the combinations to which a predetermined particle and a predetermined verb have been added such that the compound phrases are sentences.