Methods and systems for correcting transcribed audio files

• US 9,245,522 B2
• Filed: 12/23/2013
• Issued: 01/26/2016
• Est. Priority Date: 04/17/2006
• Status: Active Grant

• Current Assignee: III Holdings 1, LLC
• Original Assignee: III Holdings 1, LLC
• Inventors: Hager, Paul M.
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US14/138,609
• Publication Number:
  US 20140114658A1
• Time in Patent Office: 764 Days
• Field of Search: 704/235
• US Class Current: 1/1
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting

Abstract

Methods and systems for correcting transcribed text. One method includes receiving audio data from one or more audio data sources and transcribing the audio data based on a voice model to generate text data. The method also includes making the text data available to a plurality of users over at least one computer network and receiving corrected text data over the at least one computer network from the plurality of users. In addition, the method can include modifying the voice model based on the corrected text data.

Claims

1. A method comprising:

receiving audio data from an audio data source;

segmenting the audio data into a plurality of audio data segments and transcribing a first one of the audio data segments based on a voice model to generate first text data;

making the first text data available to at least one user over an electronic network;

receiving second corrected text data that is different than the first text data over the electronic network responsive to making the first text data available to the at least one user over the electronic network;

modifying the voice model based on the second corrected text data;

in response to modifying the voice model, performing additional transcription based on the modified voice model to generate third text data representing a portion of the received audio data, said portion of the received audio data including audio data of a second audio data segment of the plurality of audio data segments that is different than the first audio data segment.

2. The method of claim 1, wherein receiving the audio data from the audio source includes receiving the audio data from a VoIP voicemail server.

3. The method of claim 1, wherein receiving the audio data from the audio source includes receiving the audio data from a client computer over the electronic network.

4. The method of claim 1, wherein receiving the audio data from the audio source includes receiving the audio data in an e-mail message.

5. The method of claim 1, wherein receiving the audio data from the audio source includes requesting the audio data from the audio source.

6. The method of claim 5, further comprising prioritizing the audio data.

7. The method of claim 1, wherein transcribing the first audio data segment of the audio data based on the voice model to generate the first text data includes transcribing the first audio data segment based on a voice independent model to generate the first text data.

8. The method of claim 1, further comprising sending a correction notification to the at least one user or another user.

9. The method of claim 8, wherein sending the correction notification includes sending an e-mail correction notification.

10. The method of claim 1, further comprising indexing the first text data.

11. A memory device having instructions stored thereon that, in response to execution by a processing device, cause the processing device to perform operations comprising:

segmenting audio data from an audio source into a plurality of audio data segments and transcribing a first one of the audio data segments based on a voice model to generate first text data;

making the first text data available to at least one user over an electronic network;

receiving second corrected text data that is different than the first text data over the electronic network responsive to making the first text data available to the at least one user over the electronic network;

modifying the voice model based on the second corrected text data; and

performing additional transcription based on the modified voice model to generate third text data representing a portion of the received audio data, said portion of the received audio data including audio data of a second audio data segment of the plurality of audio data segments that is different than the first audio segment.

12. The memory device of claim 11, wherein the operations further comprise prioritizing the first audio data segment.

13. The memory device of claim 11, wherein transcribing the first audio data segment based on the voice model to generate the first text data includes transcribing the first audio data segment based on a voice independent model to generate the first text data.

14. The memory device of claim 11, wherein the operations further comprise sending a correction notification to the at least one user or another user.

15. The memory device of claim 14, wherein sending the correction notification includes sending an e-mail correction notification.

16. An apparatus, comprising:

means for segmenting audio data from an audio source into a plurality of audio data segments;

means for transcribing a first one of the audio data segments based on a voice model to generate first text data;

means for making the first text data available to a plurality of users over an electronic network;

means for modifying the voice model based on second corrected text data that is different from the first text data and received responsive to making the first text data available to the plurality of users over the electronic network; and

means for transcribing based on the modified voice model to generate third text data representing a portion of the audio data, said portion of the audio data including audio data of a second audio data segment of the plurality of audio data segments that is different than the first audio data segment.

17. The apparatus of claim 16, further comprising means for prioritizing the first audio data segment.

18. The apparatus of claim 16, wherein the voice model comprises a voice independent model.

19. The apparatus of claim 16, further comprising means for sending a correction notification to at least one user of the plurality of users.

20. The apparatus of claim 16, further comprising means for indexing the first text data.