Tracking Time Using Portable Recorders and Speech Recognition

• US 20080288251A1
• Filed: 07/28/2008
• Published: 11/20/2008
• Est. Priority Date: 02/16/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Cooper, James William, Byron, Donna Karen
• Granted Patent: US 7,664,638 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G04G 21/06 using voice
• CPC Class Codes: G06Q 10/109 Time management, e.g. calendars, reminders, meetings or time accounting
• CPC Class Codes: G07C 1/00 Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people registering or indicating the working of machines or vehicles G07C3/00, G07C5/00
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In general, the present invention converts speech, preferably recorded on a portable recorder, to text, analyzes the text, and determines voice commands and times when the voice commands occurred. Task names are associated with voice commands and time segments. These time segments and tasks may be packaged as time increments and stored (e.g., in a file or database) for further processing. Preferably, phrase grammar rules are used when analyzing the text, as this helps to determine voice commands. Using phrase grammar rules also allows the text to contain a variety of topics, only some of which are pertinent to tracking time.

Claims

1. A method, performed on a computer system, for tracking time using speech recognition, the method comprising the steps of:

accessing speech data;

recognizing at least two voice commands from the speech data, each voice command occurring at a different time;

determining a first time associated with a speaking of a first of the voice commands, wherein said first voice command identifies a start of a time interval;

determining a second time associated with a speaking of a second of the voice commands, wherein said second voice command identifies an end of said time interval; and

storing data identifying said time interval and data identifying one or more of said first voice command and second voice command, wherein

the speech data comprises a time stamp;

the step of determining a first time comprises;

determining an offset time between the time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the time stamp and the offset time.

2. The method of claim 1, wherein:

the speech data comprises a time stamp;

the step of determining a first time comprises;

determining an offset time between the time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the time stamp and the offset time; and

the step of determining a second time comprises;

determining a second offset time between the time stamp and a time when the second voice command is spoken; and

determining the second time through reference to the time stamp and the second offset time.

3. The method of claim 2, wherein:

the step of determining the first time through reference to the time stamp and the offset time comprises the step of adding the offset time to the time stamp to determine the first time; and

the step of determining the second time through reference to the time stamp and the second offset time comprises the step of adding the second offset time to the time stamp to determine the second time.

4. The method of claim 1, wherein:

the speech data comprises first and second time stamps;

the step of determining a first time comprises;

determining a first offset time between the first time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the first time stamp and the first offset time; and

the step of determining a second time comprises;

determining a second offset time between the second time stamp and a time when the second voice command is spoken; and

determining the second time through reference to the second time stamp and the second offset time.

5. The method of claim 1, further comprising the steps of:

recording speech onto a portable recorder; and

loading the speech data from the portable recorder to the computer system, the speech data comprising the speech and a plurality of time stamps.

6. The method of claim 1, further comprising the step of:

determining at least one task name from the text of the at least two voice commands.

7. The method of claim 6, wherein the step of determining at least one task name comprises finding the at least one task name in the text.

8. The method of claim 6, wherein the step of determining at least one task name comprises associating at least one task name to said time interval between the first and second times, wherein the at least one task name is not in the text.

9. The method of claim 6, wherein the at least one task name comprises two task names, a first task name associated with a first of the voice commands and a second task name associated with a second of the voice commands, wherein the first and second voice commands occur adjacent to each other in time, wherein the first and second task name are different, and wherein the second voice command is assumed to end a first task corresponding to the first task name and start a second task corresponding to the second task name.

10. The method of claim 6, further comprising the step of packaging the first time, second time, and one task name from the at least one task name into a time increment.

11. The method of claim 6, wherein the at least two voice commands comprises a plurality of voice commands, wherein the at least one task name comprises a plurality of task names, and wherein the method further comprises the steps of:

determining an additional plurality of voice command times, each of the voice command times associated with one of the plurality of additional voice command times;

converting each of the plurality of voice commands to text;

determining a plurality of task names from the text;

associating a task name with two of the first time, second time, or additional plurality of voice command times;

creating a plurality of time increments, each time increment comprising two times of the first time, second time, or additional plurality of voice command times and a task name; and

storing the plurality of time increments.

12. The method of claim 6, further comprising the step of determining text versions of the at least two voice commands by comparing words in the text with phrase grammar rules.

13. A system for tracking time using speech recognition, the system comprising:

a computer system comprising;

a memory that stores computer-readable code; and

a processor operatively coupled to the memory, the processor configured to implement the computer-readable code, the computer-readable code configured to;

access speech data;

recognize at least two voice commands from the speech data, each voice command occurring at a different time;

determine a first time associated with a speaking of a first of the voice commands, wherein said first voice command identifies a start of a time interval;

determine a second time associated with a speaking of a second of the voice commands, wherein said second voice command identifies an end of a time interval;

convert each of the at least two voice commands to text;

determine text versions of the at least two voice commands by comparing words in the text with phrase grammar rules; and

storing data identifying said time interval and data identifying one or more of said first voice command and second voice command, wherein

the speech data comprises a time stamp;

the step of determining a first time comprises;

determining an offset time between the time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the time stamp and the offset time.

14. The system of claim 13, wherein the speech data comprises a time stamp, and wherein the computer-readable code is further configured to:

when determining a first time;

determining an offset time between the time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the time stamp and the offset time; and

when determining a second time;

determining a second offset time between the time stamp and a time when the second voice command is spoken; and

determining the second time through reference to the time stamp and the second offset time.

15. The system of claim 13, wherein the computer-readable code is further configured to:

store one or more time increments comprised of the first time, the second time, and at least one text version of the at least two voice commands; and

place the time increments into a file having a format suitable for importing into a time and billing program.

16. The system of claim 13, wherein the system further comprises a digital personal recorder and wherein the computer-readable code is further configured to receive the speech data from the digital personal recorder.

17. An article of manufacture comprising:

a computer readable medium having computer readable code means embodied thereon, the computer readable program code means comprising;

a step to access speech data;

a step to recognize at least two voice commands from the speech data, each voice command occurring at a different time;

a step to determine a first time associated with a speaking of a first of the voice commands, wherein said first voice command identifies a start of a time interval;

a step to determine a second time associated with a speaking of a second of the voice commands, wherein said second voice command identifies an end of a time interval;

a step to convert each of the at least two voice commands to text;

a step to determine text versions of the at least two voice commands by comparing words in the text with phrase grammar rules; and

storing data identifying said time interval and data identifying one or more of said first voice command and second voice command.

the speech data comprises a time stamp;

the step of determining a first time comprises;

determining an offset time between the time stamp and a time when the first voice command is spoken; and

determining the first time through reference to the time stamp and the offset time.