Methods and systems for correcting transcribed audio files
First Claim
Patent Images
1. A method of correcting transcribed text utilizing a computer-processing system, the computer-processing system having a browser-based user interface, the method comprising:
- receiving a first plurality of audio data sets from one or more audio data sources, wherein at least two of the first plurality of audio data sets are associated with different speakers;
transcribing the first plurality of audio data sets based on a voice-independent model to generate a plurality of text data sets, wherein at least two of the plurality of text data sets are associated with different speakers;
storing the plurality of text data sets;
making the plurality of text data sets available to a plurality of users over at least one computer network through the browser-based user interface;
receiving a plurality of corrected text data sets over the at least one computer network from at least one of the plurality of users through the browser-based user interface, wherein the plurality of corrected text data sets are associated with the plurality of text data sets and at least two of the plurality of corrected text data sets are associated with different speakers;
updating the voice-independent model based on the plurality of corrected text data sets received through the browser-based interface; and
transcribing a second plurality of audio data sets based on the voice-independent model as updated, wherein at least two of the second plurality of audio data sets are associated with different speakers.
2 Assignments
0 Petitions
Accused Products
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.
120 Citations
30 Claims
-
1. A method of correcting transcribed text utilizing a computer-processing system, the computer-processing system having a browser-based user interface, the method comprising:
-
receiving a first plurality of audio data sets from one or more audio data sources, wherein at least two of the first plurality of audio data sets are associated with different speakers; transcribing the first plurality of audio data sets based on a voice-independent model to generate a plurality of text data sets, wherein at least two of the plurality of text data sets are associated with different speakers; storing the plurality of text data sets; making the plurality of text data sets available to a plurality of users over at least one computer network through the browser-based user interface; receiving a plurality of corrected text data sets over the at least one computer network from at least one of the plurality of users through the browser-based user interface, wherein the plurality of corrected text data sets are associated with the plurality of text data sets and at least two of the plurality of corrected text data sets are associated with different speakers; updating the voice-independent model based on the plurality of corrected text data sets received through the browser-based interface; and transcribing a second plurality of audio data sets based on the voice-independent model as updated, wherein at least two of the second plurality of audio data sets are associated with different speakers. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 23, 24, 25, 26)
-
-
14. A system for correcting transcribed text, the system comprising:
-
a transcription server receiving a first plurality of audio data sets from one or more audio data sources, wherein at least two of the first plurality of audio data sets are associated with different speakers; at least one translation server to transcribe the first plurality of audio data sets based on a voice-independent model to generate a plurality of text data sets, wherein at least two of the plurality of text data sets are associated with different speakers, a browser-based correction interface accessible by a plurality of users over at least one computer network and providing access to the plurality of text data sets and receiving a plurality of corrected text data sets from at least one of the plurality of users, wherein the plurality of corrected text data sets are associated with the plurality of text data sets and at least two of the plurality of corrected text data sets are associated with different speakers; and at least one training server receiving the plurality of corrected text data sets received through the browser-based connection and updating the voice-independent model based on the plurality of corrected text data sets, wherein the at least one translation server transcribes a second plurality of audio data sets based on the voice-independent model as updated, wherein at least two of the second plurality of audio data sets are associated with different speakers. - View Dependent Claims (15, 16, 17, 18)
-
-
19. A method of performing audio data transcription utilizing a computer-processing system, the computer-processing system having a browser-based interface, the method comprising:
-
obtaining first audio data from at least one audio data source; transcribing the first audio data based on a voice-independent model to generate text data; sending a message notification to an owner of the first audio data, the message notification including an address where the text data is accessible through the browser-based user interface; receiving corrections to the text data updating the voice-independent model based on the corrections; and transcribing second audio data with the voice-independent model as updated. - View Dependent Claims (20, 21, 22)
-
-
27. A method of generating transcribed text data utilizing a computer-processing system, the computer-processing system having a streaming translation server, the method comprising:
-
receiving first audio data from one or more audio data sources; routing the first audio data to the streaming translation server; transcribing the first audio data based on a voice-independent model to generate text data in substantially real-time; providing the text data to one or more devices over at least one computer network; receiving from at least one of a plurality of users a plurality of corrected text data sets related to a plurality of text data sets generated with the voice-independent model, wherein at least two of the plurality of corrected text data sets are associated with different speakers; updating the voice-independent model based on the plurality of corrected text data sets; and transcribing second audio data based on the voice-independent model as updated. - View Dependent Claims (28)
-
-
29. A method of training a voice-independent model utilizing a computer-processing system, the computer-processing system having a voice-independent model, a first transcription server, and a second transcription server, the method comprising:
-
transcribing a first plurality of audio data sets based on the voice-independent model with the first transcription server to generate a plurality of text data sets, wherein at least two of the first plurality of text data sets are associated with different speakers; making the plurality of text data sets available to a user; receiving a plurality of corrected text data sets from the user, wherein the plurality of corrected text data sets are associated with the plurality of text data sets and at least two of the plurality of corrected text data sets are associated with different speakers; updating the voice-independent model based on the plurality of corrected text data sets and the voice-independent model; transcribing a second plurality of audio data set based on the voice-independent model as updated with the first transcription server; and sharing the updated voice-independent model, as updated, with the second transcription server.
-
-
30. A method of correcting transcribed text utilizing a computer-processing system, the computer-processing system having a browser-based interface, the method comprising:
-
receiving audio data from an audio data source; transcribing a segment of the audio data to generate a corresponding text data segment based on a voice-independent model; making the text data segment available to a user through the browser-based interface; receiving a corrected text data segment from the user through the browser-based interface; updating the voice-independent model based on the corrected text data segment to pre-train the voice-independent model before transcribing a remainder of the audio data; and transcribing the remainder of the audio data based on the voice-independent model, as updated.
-
Specification