TEXT TO SPEECH INTERACTIVE VOICE RESPONSE SYSTEM

• US 20080270137A1
• Filed: 04/27/2007
• Published: 10/30/2008
• Est. Priority Date: 04/27/2007
• Status: Active Grant

• Current Assignee: Craig B. Dickson, James R. Woolsey, Stephen J. Eady
• Original Assignee: Craig B. Dickson, James R. Woolsey, Stephen J. Eady
• Inventors: Eady, Stephen J., Dickson, Craig B., Woolsey, James R.
• Granted Patent: US 7,895,041 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers

Abstract

A text to speech interactive voice response system is operable within a personal computer having a processor, data storage means and an operating system. The system comprises an input subsystem for receiving a text data stream from a source device in a predetermined format; a process control subsystem for converting the text data stream into corresponding output data items; an audio record subsystem for recording audio data to be associated with each output data item; and, a broadcast control subsystem for generating an audio broadcast based on the output data items. There is also disclosed a system management and control subsystem for user interface with the system.

Claims

1. A text to speech interactive voice response system operable within a personal computer having a processor, data storage means and an operating system, said system comprising:

a. an input subsystem for receiving a text data stream from a source device wherein said text data stream has a predetermined format, and further wherein said input subsystem converts the text data stream into a plurality of input data items;

b. a process control subsystem for receiving said plurality of input data items and converting them into a corresponding plurality of output data items, wherein each output data item of said corresponding plurality of output data items comprises a sequence of speech units;

c. an audio record subsystem for recording audio data to be associated with each speech unit of said sequence of speech units;

d. a broadcast control subsystem for generating an audio broadcast based on said audio data associated with the sequence of speech units; and

,

e. a system management and control subsystem for user interface with the system.

2. The system of claim 1 wherein the input subsystem comprises an input/filter module comprising an Input DLL module for receiving the text data stream having a predetermined application specific format.

3. The system of claim 2 wherein the input/filter module further comprises a filter DLL module for receiving the text data stream from the input DLL module, scanning the text data stream, and selecting strings of text that conform to predetermined properties.

4. The system of claim 3 wherein the filter DLL module further assigns a type value and a name value to each of said selected strings of text thereby creating an input data item corresponding to each of the selected strings of text.

5. The system of claim 4 wherein the input subsystem further comprises an input control module for receiving said input data item and adding the input data item to an input data item list.

6. The system of claim 1 wherein said process control subsystem comprises a process control module adapted for receiving the input data item from the input data item list and processing the input data item in accordance with the type value and name value of the input data item.

7. The system of claim 6 wherein a first type value and name value of the input data item specify user preview resulting in the input data item being placed on a review data item list.

8. The system of claim 6 wherein a second type value and name value of the input data item specify merging with a previously processed data item resulting in the input data item and said previously processed data item merging by way of a combine DLL module within said process control module.

9. The system of claim 6 wherein a third type value and name value of the input data time specify translation of the input data item from a non-usable code to a usable code resulting in the input data item being processed by a translate DLL module within the process control module.

10. The system of claim 6 wherein a fourth type value and name value specify that the input data item is in the form of a previously defined format resulting in a format check DLL module processing the input data item, wherein said format check DLL module resides within the process control module.

11. The system of claim 10 wherein the input data item fails said format check DLL processing resulting in the input data time being placed on an error data item list for correction through a command interface module.

12. The system of claim 6 wherein the process module assigns an input item language value to the input data item.

13. The system of claim 12 wherein the process control subsystem further comprises a parser module for receiving the input data item and the input item language value, wherein said parser module is adapted for decomposing the input data item into a plurality of speech units by selecting a vocabulary item from a vocabulary item list in accordance with the input item language value thereby forming a list of audio data items and output data items for placement on an output data item list.

14. The system of claim 1 wherein said audio record subsystem comprises a record control module and a record DLL module which cooperate to permit the user to record audio data to be associated with specific output data items, wherein the record DLL module interfaces with a plurality of audio input devices, and wherein the record control module manages the record DLL module.

15. The system of claim 14 wherein the record DLL module is an interface to a third party text-to-speech system.

16. The system of claim 1 wherein said broadcast control subsystem functions to generate an audio broadcast to at least one audio device being a sound output device, and wherein the broadcast control subsystem comprises an assembly module, a schedule control module, a schedule DLL module, an audio interface module and an audio DLL module.

17. The system of claim 16 wherein said assembly module receives output data items from the output data item list, and wherein the assembly module acts in cooperation with said schedule control module to receive schedule items and incorporate said schedule items into the output data item list to form an audio control list having appropriate speech concatenation.

18. The system of claim 17 wherein the schedule control module receives the schedule items from said schedule DLL, and wherein the schedule items define said speech concatenation.

19. The system of claim 1 wherein said system management and control subsystem comprises a command subsystem comprising a command interface module permitting user access to the vocabulary list, the input data item list, review data item list, error data item list and output data item list so that the user can review, edit or delete data items as required.

20. The system of claim 19 wherein the command interface module communicates with an event handler module for access to application-specific DLL modules.

21. The system of claim 20 wherein the command subsystem further comprises a user interface module for providing access to the system command interface module and for providing the user with a graphic interface.

22. The system of claim 21 wherein the user interface module communicates with a text DLL module for providing the appropriate user language and a batch control DLL for specifying additional processing by the user.

23. The system of claim 19 wherein the system management and control subsystem further comprises a utility control subsystem comprising a configuration control DLL module for providing a consistent method of accessing the system configuration means.

24. The system of claim 23 wherein the utility control subsystem further comprises a log control module for logging system information into a common location.

25. The system of claim 1 further comprising an intersystem control subsystem for coordinating the communication between two systems, said intersystem control subsystem comprising an intersystem DLL module for loading and managing intersystem communication;

and, an intersystem DLL module for implementing the requirements for intersystem communications.

26. A text to speech conversion method comprising the steps performed by a processor and a plurality of dynamic link libraries, of:

a. receiving a text message;

b. converting said text message into a plurality of sequential text fields;

c. associating each sequential text field of said plurality of sequential text fields with a respective input data item;

d. processing each input data item including the step of associating each input data item with a vocabulary element selected from a pre-recorded list of vocabulary elements;

e. associating said vocabulary element with an audio data file thereby generating an audio control list as an output data item list;

f. assembling said output data item list into an audio message; and

,

g. broadcasting said audio message.

27. The method of claim 26 further including the step after step b of checking each sequential text field to ensure that they conform to a predetermined format.

28. The method of claim 27 further including a preprocessing step performed between step c and step d wherein context sensitive text fields are translated.

29. The method of claim 28 wherein said text message comprises two independent messages and wherein the method further includes a step performed between step c and step d combining said two independent messages into a single output.

30. The method of claim 29 further comprising a step performed after step c of identifying error items in each data input item and placing them on an error data item list for operator review.

31. The method of claim 30 further comprising a step performed of placing data input items requiring operator review on a review data item list.

32. A computer software program having a set of instructions stored on computer readable storage medium said program for converting text to speech comprising a set of executable instructions formed into each of a plurality of interdependent modules each module comprising:

a. an text data input and filter process;

b. an input control process;

c. a kernel control process;

d. a parser process;

e. an assembly process;

f. a schedule control process;

g. an audio interface process;

h. a command interface process; and

,

i. a user interface process.

33. The computer software program of claim 33 wherein said plurality of modules comprises a plurality of sets of executable instruction comprising:

a. a first set of instructions for defining an input/filter process;

b. a second set of instructions for defining an input control process;

c. a third set of instructions for defining a kernel control process;

d. a fourth set of instructions for defining a parser process;

e. a fifth set of instructions for defining an assembly process;

f. a sixth set of instructions for defining a schedule control process;

g. a seventh set of instructions for defining an audio interface process;

h. an eighth set of instructions for defining a command interface process and;

i. a ninth set of instructions for defining a user interface process.

34. The computer program of claim 33 further comprising executable modules for:

a. event handling;

b. record control;

c. log control; and

,

d. intersystem control.