Method and apparatus for reducing conflicts between speech-enabled applications sharing speech menu

• US 7,266,498 B1
• Filed: 12/18/1998
• Issued: 09/04/2007
• Est. Priority Date: 12/18/1998
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Connelly, Jay H.
• Primary Examiner(s): ARMSTRONG, ANGELA A
• Application Number:
  US09/216,457
• Time in Patent Office: 3,182 Days
• Field of Search: 704/270, 704/275, 704/243, 704/244, 704/239, 704/240, 704/251
• US Class Current: 704/270
• CPC Class Codes: G10L 15/063 Training

Abstract

Method and apparatus are provided for developing a speech menu which is adapted to store a plurality of sound commands for a speech-enabled application. A first sound command of the plurality of sound commands is compared to a second sound command to determine an accuracy value. If the accuracy value is less than a predetermined value, then at least one of the first sound command and the second sound command is replaced with a third sound command.

Claims

1. A method of building a speech menu to control at least two devices, comprising:

identifying at least two devices, each device having at least one candidate audio command associated with it,

comparing each of the candidate audio commands of each device with previously registered audio commands to develop an accuracy value, and

adding to the speech menu those candidate audio commands for which associated accuracy values exceed a predetermined value, wherein

the predetermined value is a function of at least one of the accuracy value, a predetermined threshold value and an average accuracy value, the average accuracy value being determined as a function of an average of a plurality of prior accuracy values.

2. A method of building a speech menu to control at least two devices, comprising:

identifying at least two devices, each device having at least one candidate audio command associated with it,

comparing each of the candidate audio commands of each device with previously registered audio commands to develop an accuracy value, and

adding to the speech menu those candidate audio commands for which associated accuracy values exceed a predetermined value, wherein the accuracy value is determined according to an acoustical pattern matching procedure.

3. A set of instructions residing in a storage medium, the set of instructions capable of being executed by a processor to implement a development of a speech menu for a speech-enabled application, the method comprising the steps of:

a) comparing candidate sound commands from at least two device predetermined tables to previously-stored sound commands to determine an accuracy value therebetween; and

if the accuracy values each are less than a predetermined value, installing the candidate sound commands of each device in the speech menu.

4. The set of instructions according to claim 3, wherein the predetermined value is a function of at least one of the accuracy value, a predetermined threshold value and an average accuracy value, the average accuracy value being determined as a function of an average of a plurality of prior accuracy values.

5. The set of instructions according to claim 3, wherein the accuracy value is determined using an acoustical pattern matching procedure.

6. The set of instructions according to claim 3, wherein the candidate sound command includes at least one of a word, a phrase and at least one tone.

7. A method for building a speech menu from separate pre-existing speech menus, comprising:

determining a similarity of at least two predetermined and pre-trained audio commands from the pre-existing speech menus by comparing each audio command to the others, to determine an accuracy value; and

combining each of the at least two audio commands in a final speech menu, wherein the accuracy value for each audio command is greater than or equal to a predetermined value.

8. The method of claim 7, wherein the predetermined value is a function of at least one of the accuracy value, a predetermine threshold value and an average accuracy value, the average accuracy value being determined as a function of an average of a plurality of prior accuracy values.

9. The method of claim 7, wherein each accuracy value is determined according to an acoustical matching procedure.

10. The method of claim 7, wherein an execution command is associated with any audio command in the final speech menu.

11. The method of claim 7, wherein the candidate audio commands are selected from speech, tones, or combinations thereof.

12. The method of claim 7, wherein the determining and combining occur automatically, without user intervention.

13. A speech-enabled apparatus comprising:

a distance accuracy module capable of determining the similarity of at least two pre-trained audio commands, each pre-trained audio command being selected from a pre-existing speech menu, and capable of installing each pre-trained audio command into a final speech menu unless an accuracy value for each audio command is less than a predetermined value.

14. The speech-enabled apparatus according to claim 13, wherein the speech-enabled apparatus includes a computer.

15. The speech-enabled apparatus according to claim 13, wherein the speech-enabled apparatus is coupled to at least one device using at least one of a serial connection, a parallel connection, a dedicated card connection, an internet connection, a wireless connection, or combinations thereof.

16. The speech-enabled apparatus according to claim 13, wherein the at least one device includes at least one of a computer, a stereo system, a telephone, a VCR, a home appliance control device, a cordless computer access device, a lighting system, or combinations thereof.

17. A set of instructions residing in a storage medium, the set of instructions capable of being executed by a processor to implement development of a speech menu, the method comprising the steps of:

a) determining a similarity of at least two pre-trained audio commands from pre-existing speech menus by comparing each audio command to the others to determine an accuracy value for each audio; and

b) combining each of the at least two audio commands in a final speech menu, wherein the accuracy value for each audio command is greater than or equal to a predetermined value.

18. The set of instructions according to claim 17, wherein the predetermined value is a function of at least one of the accuracy value, a predetermined threshold value and an average accuracy value, the average accuracy value being determined as a function of an average of a plurality of prior accuracy values.