Methods and Systems for Correcting Transcribed Audio Files

Patent metadata

Field	Value
Publication number	US-2021118428-A1
Application number	US-202017089179-A
Country	US
Kind code	A1
Filing date	Nov 4, 2020
Priority date	Apr 17, 2006
Publication date	Apr 22, 2021
Grant date	—

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

1 - 10 . (canceled)

11 . A memory device having instructions stored thereon that, in response to execution by a processor, cause the processor to perform operations comprising:
generating a transcription of a first portion of audio data using a voice model, wherein the audio data comprises a single audio file with a recording of a plurality of speakers; receiving a correction to the transcription of the first portion of the audio data; generating an updated voice model based on the correction to the transcription of the first portion of the audio data; and generating a transcription of a second portion of audio data using the updated voice model.

12 . The memory device of claim 11 , wherein the voice model comprises a voice-independent model.

13 . The memory device of claim 11 , wherein at least one of the first portion of the audio data and the second portion of the audio data originates from a VoiP voicemail server.

14 . The memory device of claim 11 , wherein at least one of the first portion of the audio data and the second portion of the audio data originates from a client computer coupled to at least one computer network.

15 . The memory device of claim 11 , wherein the operations further comprise extracting at least one of the first portion of the audio data and the second portion of the audio data from an e-mail message.

16 . The memory device of claim 11 , wherein the operations further comprise requesting at least one of the first portion of the audio data and the second portion of the audio data from a remote source.

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

18 . The memory device of claim 11 , wherein the first portion of the audio data comprises 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.

19 . The memory device of claim 11 , wherein the operations further comprise determining when each of the plurality of speakers is speaking.

20 . The memory device of claim 11 , wherein the transcription of the first portion of audio data comprises a first text data set associated with one of the plurality of speakers and a second text data set associated with another one of the plurality of speakers.

21 . A method comprising:
generating a transcription of a first portion of audio data using a voice model, wherein the audio data comprises a single audio file with a recording of a plurality of speakers; receiving a correction to the transcription of the first portion of the audio data; generating an updated voice model based on the correction to the transcription of the first portion of the audio data; and generating a transcription of a second portion of audio data using the updated voice model.

22 . The method of claim 21 , wherein the voice model comprises a voice-independent model.

23 . The method of claim 21 , wherein at least one of the first portion of the audio data and the second portion of the audio data originates from a VoiP voicemail server.

24 . The method of claim 21 , wherein at least one of the first portion of the audio data and the second portion of the audio data originates from a client computer coupled to at least one computer network.

25 . The method of claim 21 , further comprising extracting at least one of the first portion of the audio data and the second portion of the audio data from an e-mail message.

26 . The method of claim 21 , further comprising requesting at least one of the first portion of the audio data and the second portion of the audio data from a remote source.

27 . The method of claim 21 , wherein the first portion of the audio data comprises 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.

28 . The method of claim 21 , further comprising determining when each of the plurality of speakers is speaking.

29 . The method of claim 21 , wherein the transcription of the first portion of audio data comprises a first text data set associated with one of the plurality of speakers and a second text data set associated with another one of the plurality of speakers.

30 . A system comprising:
means for generating a transcription of a first portion of audio data using a voice model, wherein the audio data comprises a single audio file with a recording of a plurality of speakers; means for receiving a correction to the transcription of the first portion of the audio data; means for generating an updated voice model based on the correction to the transcription of the first portion of the audio data; and means for generating a transcription of a second portion of audio data using the updated voice model.

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

• G10L15/18 Primary

  using natural language modelling · CPC title

• G06F16/31

  Indexing; Data structures therefor; Storage structures · CPC title

• G10L15/065

  Adaptation · CPC title