Systems and methods of interpreting speech data

• US 10,043,513 B2
• Filed: 03/09/2018
• Issued: 08/07/2018
• Est. Priority Date: 06/05/2014
• Status: Active Grant

• Current Assignee: Interdev Technologies Inc. (Valsef Group)
• Original Assignee: Interdev Technologies Inc. (Valsef Group)
• Inventors: Rice, Janet M., Liang, Peng, Kuehn, Terence W.
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US15/916,833
• Publication Number:
  US 20180197538A1
• Time in Patent Office: 151 Days
• Field of Search: None
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 19/26 Pre-filtering or post-filtering
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence
• CPC Class Codes: H04R 29/006 Microphone matching

Abstract

Method and systems are provided for interpreting speech data. A method and system for recognizing speech involving a filter module to generate a set of processed audio data based on raw audio data; a translation module to provide a set of translation results for the raw audio data; and a decision module to select the text data that represents the raw audio data. A method for minimizing noise in audio signals received by a microphone array is also described. A method and system of automatic entry of data into one or more data fields involving receiving a processed audio data; and operating a processing module to: search in a trigger dictionary for a field identifier that corresponds to the trigger identifier; identify a data field associated with a data field identifier corresponding to the field identifier; and providing content data associated with the trigger identifier to the identified data field.

Claims

1. A method of minimizing noise in audio signals received by a microphone array for automatic entry into one or more data fields, the microphone array being in communication with a speech recognition system, the method comprising:

providing a principal microphone and one or more supplemental microphones in the microphone array for receiving a principal audio signal and one or more supplemental audio signals respectively, the principal microphone and each supplemental microphone being spaced from one another;

for each supplemental microphone;

determining a component phase shift for calibrating that supplemental microphone;

determining an array phase difference based on a spacing between the principal microphone and that supplemental microphone, the array phase difference being relative to the principal audio signal;

determining a phase shift associated with a supplemental audio signal received by that supplemental microphone with reference to the component phase shift;

determining whether any portion of the supplemental audio signal is associated with a respective phase shift that is different from the array phase difference;

in response to determining that a portion of the supplemental audio signal is associated with a different phase shift from the array phase difference, identifying frequencies associated with that portion of the supplemental audio signal; and

removing that portion of the supplemental audio signal and a portion of the principal audio signal associated with the identified frequencies;

receiving a processed audio data from the microphone array, the processed audio data including a trigger identifier;

operating the speech recognition system to;

search in a trigger dictionary for a field identifier that corresponds to the trigger identifier, the trigger dictionary including a plurality of trigger identifiers and each trigger identifier is associated with one or more field identifiers;

identify, from the one or more data fields, a data field that is associated with a data field identifier corresponding to the field identifier, the identified data field is provided for receiving data associated with the trigger identifier; and

providing content data associated with the trigger identifier to the identified data field.

2. The method of claim 1, wherein providing the content data associated with the trigger identifier to the identified data field comprises:

identifying, from the processed audio data, a content data associated with the trigger identifier, and entering the content data into the identified data field.

3. The method of claim 2, wherein identifying from the processed audio data the content data associated with the trigger identifier comprises:

determining a content source for the identified data field based on the trigger identifier, the content source indicating an origin of the content data to be entered into the identified data field; and

receiving the content data associated with the trigger identifier from the determined content source.

4. The method of claim 3, wherein:

the content source comprises the processed audio data, the processed audio data including the content data associated with the trigger identifier.

5. The method of claim 4, wherein identifying from the processed audio data the content data comprises:

providing a user control for receiving an input control signal to access a portion of the processed audio data corresponding to the content data.

6. The method of claim 4, wherein identifying the data field comprises:

in response to failing to identify the data field that is associated with the data field identifier corresponding to the field identifier, indicating the content data associated with the trigger identifier requires additional analysis in order to be entered into the respective data field.

7. The method of claim 6 further comprises:

storing, in the memory, the content data associated with that trigger identifier; and

associating that content data with a manual analysis identifier for indicating that content data requires additional analysis.

8. The method of claim 4, wherein:

each trigger identifier in the trigger dictionary is associated with one or more expected contents, each expected content indicating data that is acceptable by the corresponding data field; and

identifying from the processed audio data the content data comprises determining whether the content data corresponds with any expected content associated with that trigger identifier.

9. The method of claim 8 comprises:

in response to determining the content data fails to correspond to any expected content, indicating the content data associated with that trigger identifier requires additional analysis in order to be inputted into the respective data field.

10. The method of claim 9 comprises:

storing, in a memory, the content data associated with that trigger identifier; and

associating that content data with a manual analysis identifier for indicating that content data requires additional analysis.

11. A system of minimizing noise in audio signals received by a microphone array for automatic entry into one or more data fields, the system comprising:

a principal microphone and one or more supplemental microphones in the microphone array for receiving a principal audio signal and one or more supplemental audio signals respectively, the principal microphone and each supplemental microphone being spaced from one another;

a memory to store a trigger dictionary;

a processor operable to;

for each supplemental microphone;

determine a component phase shift for calibrating that supplemental microphone;

determine an array phase difference based on a spacing between the principal microphone and that supplemental microphone, the array phase difference being relative to the principal audio signal;

determine a phase shift associated with a supplemental audio signal received by that supplemental microphone with reference to the component phase shift;

determine whether any portion of the supplemental audio signal is associated with a respective phase shift that is different from the array phase difference;

in response to determining that a portion of the supplemental audio signal is associated with a different phase shift from the array phase difference, identify frequencies associated with that portion of the supplemental audio signal; and

remove that portion of the supplemental audio signal and a portion of the principal audio signal associated with the identified frequencies;

receive the processed audio data from the microphone array, the processed audio data including a trigger identifier;

access the memory to search in the trigger dictionary for a field identifier that corresponds to the trigger identifier, the trigger dictionary including a plurality of trigger identifiers and each trigger identifier is associated with one or more field identifiers;

identify, from the one or more data fields, a data field that is associated with a data field identifier corresponding to the field identifier, the identified data field is provided for receiving data associated with the trigger identifier; and

provide content data associated with the trigger identifier to the identified data field.

12. The system of claim 11, wherein the processor is operable to:

determine a content source for the identified data field based on the trigger identifier, the content source indicating an origin of the content data to be entered into the identified data field; and

receive the content data associated with the trigger identifier from the determined content source.

13. The system of claim 12, wherein:

the content source comprises the processed audio data, the processed audio data including the content data associated with the trigger identifier.

14. The system of claim 13, wherein the processor is operable to:

provide a user control for receiving an input control signal to access a portion of the processed audio data corresponding to the content data.

15. The system of claim 13, wherein the processor is operable to, in response to failing to identify a data field, indicate the content data associated with the trigger identifier requires additional analysis in order to be inputted into the respective data field.

16. The system of claim 15, wherein the processor is operable to:

store, in the memory, the content data associated with that trigger identifier; and

associate that content data with a manual analysis identifier for indicating that content data requires additional analysis.

17. The system of claim 13, wherein:

each trigger identifier in the trigger dictionary is associated with one or more expected contents, each expected content indicating data that is acceptable by the corresponding data field; and

the processor is operable to determine whether the content data corresponds with any expected content associated with that trigger identifier.

18. The system of claim 17, wherein the processor is operable to, in response to determining the content data fails to correspond to any expected content, indicate the content data associated with that trigger identifier requires additional analysis in order to be inputted into the respective data field.

19. The system of claim 18, wherein the processor is operable to:

store, in the memory, the content data associated with that trigger identifier; and

associate that content data with a manual analysis identifier for indicating that content data requires additional analysis.

20. The system of claim 12, wherein:

the content source comprises an external device; and

the processor is operable to initiate communication with the external device.