Method and a device for recognizing speech

• US 6,694,295 B2
• Filed: 05/17/1999
• Issued: 02/17/2004
• Est. Priority Date: 05/25/1998
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Mobile Phones UK Limited (Nokia Corporation)
• Inventors: Lindholm, Christian, Laurila, Kari
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/313,142
• Publication Number:
  US 20020032567A1
• Time in Patent Office: 1,737 Days
• Field of Search: 704/235, 704/251, 704/252, 704/255, 704/256, 704/270, 704/275, 704/276, 704/254, 382/116
• US Class Current: 704/252
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

According to the invention, speech recognition can be limited to a smaller number making use of commands (16, 17) given by a user. By means of a method and device, according to the invention, it is also possible to activate a speech recognition device by making use, in the activation, of an existing keyboard or a touch-sensitive screen of the device. A method, according to the invention, provides the user with a logical way to activate the speech recognition device in the device simultaneously providing an improved capacity of the speech recognition device. According to the invention, it is also possible to carry out the speech recognition process by making use of commands given by the user irrespective of how the speech recognition device itself is activated. According to an embodiment of the invention, the device comprises a touch-sensitive screen or surface, in which case the information about a single letter or several letters written on the screen is transmitted to the speech recognition device, whereupon speech recognition is limited to words, wherein the letters in question occur. Speech recognition is most preferably limited to a name beginning with the letter written on the touch screen by the user.

Claims

1. A method for selecting a sub menu item of a prestored user interface menu structure by recognizing an utterance of a user with a device, wherein a set of models of the utterances have been stored in advance in the device for speech recognition, said models relating to menu items in the prestored user interface menu structure, and wherein the utterance of the user is received and compared with said prestored set of models of the utterances and, on the basis of the comparison, a recognition decision is made by the device, the method comprising the steps of:

the user providing a qualifier before said comparison limiting said comparison by touching the device, the qualifier identifying a menu item in said prestored user interface menu structure of the device, and

wherein the device performs the steps of;

selecting a sub-set of models of the utterances from said prestored models of the utterances before said comparison, on the basis of the qualifier provided by the user, said sub-set of models of the utterances identifying at least one sub-menu item of said menu item of the prestored user interface menu structure identified by said qualifier,

making the recognition decision based on a limited comparison by comparing the utterance of the user with said sub-set of models of the utterances, and

selecting one sub-menu item of said menu item of the prestored user interface menu structure on the basis of the recognition decision.

2. A method according to claim 1, wherein said device comprises a speech recognition device that is activated in response to the qualifier provided by the user.

3. A method according to claim 2, wherein the user is enabled to provide said qualifier as a press-and-hold.

4. A method according to claim 1, wherein the user is enabled to provide said qualifier by pressing a key.

5. A method according to claim 4, wherein the user is enabled to provide said qualifier as a press-and-hold.

6. A method according to claim 1, wherein the user is enabled to provide said qualifier by writing an alphanumeric character on a touch-sensitive surface of the device.

8. A method according to claim 2, wherein said device is a speech recognition device that is activated in response to the qualifier provided by the user.

13. A device according to claim 2, wherein the means for receiving the qualifier from the user comprises a keyboard.

14. A device according to claim 2, wherein the means for receiving the qualifier from the user comprises a touch-sensitive surface.

15. A device according to claim 2, wherein said means for selecting a sub-set of models and said means for activating said comparison means are activated in response to the qualifier received from the user.

7. A method for using a device to select a sub-menu item of a prestored user interface menu structure by recognizing an utterance of a user, wherein a set of models of user utterances have been stored in advance for speech recognition, said models relating to menu items in the prestored user interface menu structure, and wherein the utterance of the user is received and compared with said prestored set of models of the utterances and, on the basis of the comparison, a recognition decision is made regarding the word uttered, the method comprising the steps of:

providing said prestored menu structure for the device relating proposed words with a prestored set of models of user utterances,

making a first recognition decision, in response to a set of proposed words uttered by a user, by making a comparison in the device of the utterance of the user with the prestored set of models of the utterances in the prestored user interface menu structure, with the device performing said first recognition decision by selecting a set of proposed words in the prestored user interface menu structure based on said comparison,

enabling the user to provide a qualifier limiting the comparison by touching the device for selecting a sub-set of models of the utterances, the qualifier identifying a menu item in the prestored user interface menu structure of the device and said sub-set of models of the utterances being sub-menu items of said menu item the prestored user interface menu structure identified by said qualifier, and

wherein the device performs the further steps of;

making a final recognition decision by making a comparison in the device of said each word of said set of proposed words of the first recognition decision with said sub-set of models of the utterances, and

selecting one sub-menu item of said menu item of the prestored user interface menu structure on the basis of the final recognition decision.

9. A method according to claim 7, wherein the user is enabled to provide said qualifier by pressing a key.

10. A method according to claim 7, wherein the user is enabled to provide said qualifier by writing an alphanumeric character on a touch-sensitive surface of the device.

11. A method according to claim 10, wherein the user is enabled to provide said qualifier as a press-and-hold.

12. A speech recognition device for selecting a sub menu item of a prestored menu structure by recognizing the utterance of a user, the device comprising:

memory means for storing a set of models of the utterance of a user,

means for providing a prestored user interface menu structure containing menu items relating to said set of models of user utterances,

means for receiving the utterance of the user,

comparison means for carrying out the recognition decision process by comparing the utterance of the user with the set of models of the utterances stored in the memory means,

means for receiving a qualifier from the user in response to the user touching the device, said qualifier identifying a menu item in said prestored user interface menu structure,

means for selecting a sub-set from the set of stored models of the utterances before activation of said comparison means, on the basis of the qualifier received from the user, for limiting the comparison made by the comparison means to said sub-set of models of the utterances, said sub-set of models of the utterances identifying sub items of the menu item, identified by the qualifier, in said prestored user interface menu structure,

means for activating said comparison means to make the recognition decision by comparing the utterance of the user with said sub-set of models of the utterances, and

means for selecting one sub-menu item of said menu item prestored user interface menu structure on the basis of the recognition decision.

16. A speech recognition device according to claim 12, further comprising means for identifying said set of models of the utterances as sub-menu items in the menu structure.

17. A speech recognition device for selecting a sub menu item of a prestored user interface menu structure by recognizing an utterance of a user, the device comprising:

memory means for storing models of the utterances,

means for receiving the utterance of the user,

first comparison means for carrying out a first recognition decision process by comparing the utterance of the user with the models of the utterances stored in the memory means, said models of the utterances relating to user interface menu items of the prestored user interface menu structure, said first recognition decision comprising a set of proposed words relating to a set of user interface menu items of the prestored user interface menu structure,

means for receiving a qualifier from the user in response to the user touching the device, said qualifier identifying a menu item in said prestored user interface menu structure,

means for selecting a set from the stored models of the utterances, on the basis of the qualifier received from the user, for limiting the comparison made by the first comparison means to said set of models of the utterances, said set of models of the utterances relating to sub-items of said menu item of the prestored user interface menu structure identified by said qualifier,

second comparison means for carrying our a final recognition decision process by comparing each word of said set of proposed words of the first recognition decision and said set of models of the utterances, and

means for selecting one word of the set of proposed words, said word relating to a sub-menu item of the prestored user interface menu structure, in order to select said sub-menu item of said menu item, on the basis of the final recognition decision.

18. A method for selecting a sub-menu item of a prestored user interface menu structure by recognizing an utterance of a user with a device, wherein a set of models of the utterances have been stored in advance in the device for speech recognition, said models relating to menu items in the prestored user interface menu structure, and wherein the utterance of the user is received and compared with said prestored set of models of the utterances and, on the basis of the comparison, a recognition decision is made by the device, the method comprising the steps of:

the user providing a qualifier before said comparison limiting said comparison by touching the device, the qualifier identifying a menu item in said prestored user interface menu structure of the device, and

wherein the device performs the steps of;

selecting a sub-set of models of the utterances from said prestored models of the utterances before said comparison, on the basis of the qualifier provided by the user, said sub-set of models of the utterances identifying at least one sub-menu item of said menu item of the prestored user interface menu structure identified by said qualifier,

making the recognition decision based on a limited comparison by comparing the utterance of the user with said sub-set of models of the utterances, and

selecting one sub-menu item of said menu item of the prestored user interface menu structure on the basis of the recognition decision,

wherein the user is enabled to provide said qualifier by writing an alphanumeric character on a touch-sensitive surface of the device.

19. A method for selecting a sub-menu item of a prestored user interface menu structure by recognizing an utterance of a user with a device, wherein a set of models of the utterances have been stored in advance in the device for speech recognition, said models relating to menu items in the prestored user interface menu structure, and wherein the utterance of the user is received and compared with said prestored set of models of the utterances and, on the basis of the comparison, a recognition decision is made by the device, the method comprising the steps of:

the user providing a qualifier before said comparison limiting said comparison by touching the device, the qualifier identifying a menu item in said prestored user interface menu structure of the device, and

wherein the device performs the steps of;

selecting a sub-set of models of the utterances from said prestored models of the utterances before said comparison, on the basis of the qualifier provided by the user, said sub-set of models of the utterances identifying at least one sub-menu item of said menu item of the prestored user interface menu structure identified by said qualifier,

making the recognition decision based on a limited comparison by comparing the utterance of the user with said sub-set of models of the utterances, and

selecting one sub-menu item of said menu item of the prestored user interface menu structure on the basis of the recognition decision,

wherein said device comprises a speech recognition device that is activated in response to the qualifier provided by the user, and

wherein the user is enabled to provide said qualifier as a press-and-hold.

20. A speech recognition device for selecting a sub-menu item of a prestored menu structure by recognizing the utterance of a user, the device comprising:

memory means for storing a set of models of the utterance of a user,

means for providing a prestored user interface menu structure containing menu items relating to said set of models of user utterances,

means for receiving the utterance of the user,

comparison means for carrying out the recognition decision process by comparing the utterance of the user with the set of models of the utterances stored in the memory means,

means for receiving a qualifier from the user in response to the user touching the device, said qualifier identifying a menu item in said prestored user interface menu structure,

means for selecting a sub-set from the set of stored models of the utterances before activation of said comparison means, on the basis of the qualifier received from the user, for limiting the comparison means to said sub-set of models of the utterances, said sub-set of models of the utterances identifying sub items of the menu item, identified by the qualifier, in said prestored user interface menu structure,

means for activating said comparison means to make the recognition decision by comparing the utterance of the user with said sub-set of models of the utterances, and

means for selecting one sub-menu item of said menu item prestored user interface menu structure on the basis of the recognition decision,

wherein the means for receiving the qualifier from the user comprises a touch-sensitive surface.

21. A method for selecting a sub menu item of a prestored user interface menu structure by recognizing an utterance of a user with a device, wherein a set of models of the utterances have been stored in advance in the device for speech recognition, said models relating to menu items in the prestored user interface menu structure, and wherein the utterance of the user is received and compared with said prestored set of models of the utterances and, on the basis of the comparison, a recognition decision is made by the device, the method comprising the steps of:

the user providing a qualifier before said comparison limiting said comparison by touching the device, the qualifier identifying a menu item in said prestored user interface menu structure of the device, and

wherein the device performs the steps of;

selecting a sub-set of models of the utterances from said prestored models of the utterances before said comparison, on the basis of the qualifier provided by the user, said sub-set of models of the utterances identifying at least one sub-menu item of said menu item of the prestored user interface menu structure identified by said qualifier,

making the recognition decision based on a limited comparison by comparing the utterance of the user with said sub-set of models of the utterances, and

selecting one sub-menu item of said menu item of the prestored user interface menu structure on the basis of the recognition decision,

wherein the user is enabled to provide said qualifier by pressing a key, and

wherein the user is enabled to provide said qualifier as a press-and-hold.