System and method for processing speech

• US 9,350,862 B2
• Filed: 07/10/2015
• Issued: 05/24/2016
• Est. Priority Date: 12/06/2004
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: Interactions, LLC
• Inventors: Bushey, Robert R., Knott, Benjamin Anthony, Martin, John Mills, Korth, Sarah
• Primary Examiner(s): Phan, Joseph T
• Application Number:
  US14/796,351
• Publication Number:
  US 20150319304A1
• Time in Patent Office: 319 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2011 Service processing based on information specified by a party before or during a call, e.g. information, tone or routing selection
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends

Abstract

Systems and methods for processing audio are provided. The system may include a processor to convert an audio input received via a call to text. The processor may perform a comparison between a portion of the text to one or more phrases included in a table. The processor may also make a selection of at least one of a first object or a first action based on the comparison. The processor may further route the call based on the at least one of the first object or the first action.

Claims

1. A computer system comprising:

a memory; and

a processor coupled to the memory, wherein the memory stores instructions that,

when executed by the processor, cause the processor to perform operations comprising;

determining a first set of objects and a second set of actions from text of a call;

determining that a particular object of the first set is included in a first portion of a synonym table;

replacing the particular object in the first set with a synonym for the particular object from the synonym table to form a modified first set, wherein each object in the modified first set is associated with a confidence value;

pairing an object from the modified first set with an action from the second set to form an object-action pair, wherein the object of the object-action pair is selected to be paired with the action based on the confidence value of the object; and

routing the call based on the object-action pair.

2. The system of claim 1, wherein the audio input is a speech input.

3. The system of claim 1, wherein the text is associated with a word string.

4. The system of claim 1, wherein the object of the object-action pair is selected to be paired with the action based on a business rule.

5. The system of claim 1, wherein the operation of replacing the particular object in the first set includes changing a confidence value associated with the particular object.

6. The system of claim 1, wherein the operations further comprise identifying a destination location in a routing table based on the object-action pair.

7. The system of claim 6, wherein the operation of routing the call includes routing the call to the destination location.

8. A computer-implemented method performed by a call routing system, the method comprising:

determining a first set of objects and a second set of actions from text of a call;

determining, at the call routing system, that a particular action of the second set is included in a first portion of a synonym table;

replacing, at the call routing system, the particular action in the second set with a synonym for the particular action from the synonym table to form a modified second set, wherein each action of the modified second set is associated with a corresponding probability value that represents a probability that the action corresponds to a voice command of a caller;

pairing, at the call routing system, an object from the first set with an action from the modified second set to form an object-action pair, wherein the action of the object-action pair is selected to be paired with the object based on the probability value of the action; and

routing the call at the call routing system based on the object-action pair.

9. The method of claim 8, wherein determining the first set of objects and the second set of actions comprises parsing the text.

10. The method of claim 8, wherein routing the call based on the object-action pair comprises:

determining a routing location from a routing table based on the object-action pair; and

routing, the call to the routing location.

11. The method of claim 8, wherein the call is a voice over Internet protocol call.

12. The computerized method of claim 8, further comprising receiving the audio input via a web-based interface or a speech recognition interface of the call routing system.

13. A non-transitory computer-readable storage medium comprising instructions executable by a processor to perform operations including:

parsing text of a call to determine an action;

determining that the action is included in a first portion of a synonym table;

replacing the action with a synonym for the action from the synonym table to form a modified action, wherein each action of the modified second set is associated with a corresponding probability value that represents a probability that the action corresponds to a voice command of a caller;

pairing the modified action with an object from a set of objects based on the text to form an object-action pair, wherein the action of the object-action pair is selected to be paired with the object based on the probability value of the action;

determining a destination from a routing table based on the object-action pair; and

routing the call to the destination.

14. The computer-readable storage device of claim 13, wherein the object is a particular synonym from the synonym table that replaces a particular object parsed from the text.

15. The computer-readable storage device of claim 13, wherein the action corresponds to a word string of the text.

16. The computer-readable storage device of claim 15, wherein the word string comprises a verb.