Methods and systems for correcting transcribed audio files

Patent metadata

Field	Value
Publication number	US-10861438-B2
Application number	US-201715826110-A
Country	US
Kind code	B2
Filing date	Nov 29, 2017
Priority date	Apr 17, 2006
Publication date	Dec 8, 2020
Grant date	Dec 8, 2020

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.

First claim

The invention claimed is:

1. A memory device having instructions stored thereon that, in response to execution by a processing device, cause the processing device to perform operations comprising:
determining when a first speaker is speaking and when a second speaker is speaking in audio data comprising both speech of the first speaker and speech of the second speaker, wherein the second speaker is different from the first speaker, wherein the audio data comprises a single audio file;
transcribing a first portion of the audio data based on one voice model to generate text data sets, wherein a first text data set of the text data sets is associated with the first speaker and a second text data set of the text data sets is associated with the second speaker, and wherein the voice model comprises a voice-independent model;
in response to receiving at least one corrected text data set corresponding to the at least one of the text data sets, updating the voice model based on the at least one corrected text data set; and
transcribing a second portion of the audio data based on the voice model as updated.

2. The memory device of claim 1 , wherein the first portion of the audio data or the second portion of the audio data originates from a VoiP voicemail server.

3. The memory device of claim 1 , wherein the first portion of the audio data or the second portion of the audio data originates from a client computer coupled to at least one computer network.

4. The memory device of claim 1 , wherein the operations further comprise extracting the first portion of the audio data or the second portion of the audio data from an e-mail message.

5. The memory device of claim 1 , wherein the operations further comprise requesting the first portion of the audio data or the second portion of the audio data from a remote audio data source.

6. The memory device of claim 5 , wherein the operations further comprise prioritizing the first portion of the audio data.

7. The memory device of claim 1 , wherein the operations further comprise sending an e-mail message notification to a user, the e-mail message notification identifying the at least one of the text data sets.

8. The memory device of claim 1 , wherein the operations further comprise delivering the at least one corrected text data set to a destination.

9. The memory device of claim 8 , wherein the operations further comprise receiving information identifying the destination from a user.

10. The memory device of claim 1 , wherein the first portion of the audio data includes a first remotely user-selected portion of the audio data, and wherein the second portion of the audio data includes a second remotely user-selected portion of the audio data.

11. The memory device of claim 1 , wherein the operations further comprise making at least one of the text data sets available to a plurality of users over the at least one computer network, wherein the at least one corrected text data set is received over the at least one computer network from at least one user of the plurality of users.

12. A method comprising:
determining when a first speaker is speaking and when a second speaker is speaking in audio data comprising both speech of the first speaker and speech of the second speaker, wherein the second speaker is different from the first speaker, wherein the audio data comprises a single audio file;
transcribing a first portion of audio data based on one voice model to generate first text data sets, wherein one of the first text data sets is associated with the first speaker, wherein another one of the first text data sets is associated with the second speaker, and wherein the voice model comprises a voice-independent model;
in response to receiving at least one corrected text data set, updating the voice mod(based on the at least one corrected text data set; and
transcribing a second portion of the audio data based on the voice model voice as updated to generate second text data sets.

13. The method of claim 12 , wherein the first portion of the audio data or the second portion of the audio data originates from a VoiP voicemail server.

14. The method of claim 12 , wherein the first portion of the audio data or the second portion of the audio data originates from a client computer coupled to at least one computer network.

15. The method of claim 12 , further comprising extracting the first portion of the audio data or the second portion of the audio data from an e-mail message.

16. The method of claim 12 , further comprising requesting the first portion of the audio data or the second portion of the audio data from a remote audio data source.

17. The method of claim 16 , further comprising prioritizing the first portion of the audio data.

18. The method of claim 12 , further comprising sending an e-mail message notification to a user, the e-mail message notification identifying the at least one of the first text data sets.

19. The method of claim 12 , further comprising delivering the at least one corrected text data set to a destination.

20. The method of claim 19 , further comprising receiving information identifying the destination from a user.

Assignees

• Iii Holdings 1 Llc

Inventors

• Hager Paul M

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/00 Primary

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G06F16/31

  Indexing; Data structures therefor; Storage structures · CPC title

• G10L15/063 Primary

  Training · CPC title

• G10L15/18 Primary

  using natural language modelling · CPC title