Speech-to-text dictation system with audio message capability

• US 5,857,099 A
• Filed: 07/17/1997
• Issued: 01/05/1999
• Est. Priority Date: 09/27/1996
• Status: Expired due to Term

• Current Assignee: Allvoice Developments US LLC
• Original Assignee: Allvoice Computing PLC (Allvoice Developments US LLC)
• Inventors: Corbett, Steven Norman, Heard, Allen James, Mitchell, John C., Daniel, Nicholas John
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US08/896,105
• Time in Patent Office: 537 Days
• Field of Search: 704/235, 704/270, 707/530
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Data processing apparatus is disclosed for receiving recognition data from a speech recognition engine and its corresponding dictated audio data where the recognition data includes recognised words or characters. A display displays the recognised words or characters and the recognised words or characters are stored as a file together with the corresponding audio data. Link data is formed to link the position of the words or characters in the file and the position of the corresponding audio component in the audio data. The recognised words or characters can be processed without loosing the audio data.

Claims

1. A method of processing data comprising:

receiving recognition data from a speech recognition engine and audio data, the recognition data including recognised characters;

displaying the recognised characters;

storing the recognised characters as a file;

selectively disabling one of the display and storage of the recognised characters said the speech recognition engine for a period of time; and

storing received audio data during said period of time as an audio message associated with the file.

2. A method according to claim 1 including the steps of reading the file for display and said audio message associated with the file;

and playing back the read audio message.

3. A method of processing data comprising reading a file of recognised characters and an associated audio message stored using the method of claim 1;

displaying the read recognised characters; and

audibly outputting the read audio message.

4. Data processing apparatus comprising

means for receiving recognition data from a speech recognition engine and audio data, the recognition data including recognised characters corresponding to received audio data;

display means for displaying the recognised characters;

storage means for storing the recognised characters as a file;

means for selectively disabling one of the display and storage of the recognised characters and the speech recognition engine for a period of time; and

means for storing received audio data during said period of time in said storage means as an audio message associated with the file.

5. Data processing apparatus as claimed in claim 4 including reading means for reading the file for display on said display means and for reading said audio message associated with the file;

and

audio play back means for playing back the read audio message.

6. Data processing apparatus comprising means for reading a file and associated audio message stored using the data processing apparatus of claim 4, display means for displaying the file, and audio playback means for playing back the audio message.

7. A computer usable medium having computer readable instructions stored therein for causing the processor in a data processing apparatus to process signals defining a string of characters and audio data to store the characters and the audio data, the instructions comprising instructions for

a) causing the processor to receive the string of characters from a speech recognition engine and the audio data;

b) causing the processor to generate an image of the characters on a display;

c) causing the processor to generate an image of the characters as a file;

d) causing the processor to selectively disable one of the display and storage of the characters and the speech recognition engine for a period of time; and

e) causing the processor to store received audio data during said period of time as an audio message associated with the file.

8. A computer usable medium as claimed in claim 7 including instructions for

a) causing the processor to read the stored characters and audio message;

b) causing the processor to generate an image of the characters for display; and

c) causing the processor to send the audio message to an audio play back device.

9. A data processing method comprising inputting audio data;

and

selecting one of receiving recognition data from a speech recognition engine and storing the recognition data and corresponding audio data in a file, said recognition data including recognised characters corresponding to input audio data, or storing only the input audio data in association with a file of recognition data.

10. A data processing method according to claim 9 including the step of reading the file of recognition data and any audio data associated with the file having no corresponding recognition data, and audibly outputting the read audio data associated with the file.

11. Data processing apparatus comprising:

input means for inputting audio data;

means for receiving recognition data from a speech recognition engine, said recognition data including recognised characters corresponding to input audio data;

storage means for storing the recognised characters in a file and for storing the audio data; and

user operable selection means for selecting one of the recognised characters and corresponding audio data for storage in said storage means, or only audio data for storage in said storage means in association with a file of recognised characters.

12. Data processing apparatus according to claim 11 including means for reading the file of recognised characters and any audio data associated with the file having no corresponding recognised characters, and audio output means for audibly outputting the read audio data associated with the file.

13. A computer usable medium having computer readable instructions stored therein for causing the processor in a data processing apparatus to process signals defining recognition data from a speech recognition engine and audio data to store the recognition data and the audio data, the instructions comprising instructions for:

a) causing the processor to receive audio data signals;

b) causing the processor to receive recognition data signals from a speech recognition engine; and

c) selectively causing the processor to store the recognition data signals in a file in storage means and to store corresponding audio data signals in said storage means, or to store only the audio data signals in association with a file of recognition data signals in said storage means.

14. A computer usable medium according to claim 13 including instructions for:

a) causing the processor to read the stored recognition data signals and audio data signals; and

b) causing the processor to generate an audible output using the read audio data signals.

15. A speech recognition method comprising:

inputting speech data;

selectively performing speech recognition on input speech data to generate the recognised characters;

visibly outputting the recognised characters;

storing recognised characters corresponding to a portion of input speech data as a file when speech recognition is performed; and

storing a portion of the input speech data in association with a file of recognised characters as an audio message when speech recognition is not performed.

16. A speech recognition method according to claim 15 including:

reading one of the stored files of recognised characters for visible output;

reading any audio message associated with the read file; and

audibly outputting any read audio message.

17. A speech recognition method comprising:

reading a file of recognised characters and any associated audio message stored using the method of claim 15;

visibly outputting the recognised characters of the read file; and

audibly outputting any read audio message.

18. Speech recognition apparatus comprising:

input means for inputting speech data;

recogniser means for receiving input speech data and for selectively performing speech recognition to generate recognised characters;

output means for visibly outputting the recognised characters, storage means for storing the input speech data and recognised characters;

storage control means for;

controlling said storage means to store recognised characters from said recogniser means corresponding to a portion of input speech data as a file when said recogniser means is operating, and

for controlling said storage means to store a portion of the input speech data in association with a file of recognised characters as an audio message when said recogniser means is not operating.

19. Speech recognition apparatus according to claim 18 including means for reading one of the stored files of recognised characters for visible output on said visible output means, and for reading any audio message associated with the read file;

and audible output means for audibly outputting any read audio message.

20. Speech recognition apparatus comprising means for reading a file of recognised characters and any associated audio message stored using the apparatus of claim 18;

output means for visibly outputting the recognised characters of the read file; and

audible output means for audibly outputting any read audio message.

21. A computer usable medium having computer readable instructions stored therein for causing a processor in a speech recognition apparatus to process signal defining recognised characters and audio data to store the recognised characters and audio data, the instructions comprising instructions for:

a) causing the processor to receive input speech data;

b) causing the processor to perform speech recognition on the input speech data to generate recognised characters;

c) causing the processor to visibly output the recognised characters;

d) causing the processor to store the input speech data and recognised characters, in storage means; and

e) causing the processor to control said storage means to store recognised characters corresponding to a portion of input speech data as a file when speech recognition is being carried out, and to control said storage means to store a portion of the input speech data in association with a file of recognised characters as an audio message when speech recognition is not being carried out.

22. A computer usable medium according to claim 21 including instructions for:

a) causing the processor to read one of the stored files of recognised characters and any associated audio message;

b) causing the processor to visibly output the read recognised characters; and

c) causing the processor to audibly output any read audio message.