Method of labelling takes in an audio editing system
First Claim
Patent Images
1. A method of automatically labeling takes in an audio editing system comprising:
- (a) providing a workstation having memory means and a processor unit associated therewith;
(b) programming said workstation with operating system software;
(c) accessing with said workstation a digital data file corresponding to a speech take;
(d) interfacing said system software with speech recognition software;
(e) subsequent to said interfacing and said accessing, implementing said speech recognition software to translate at least a portion of said digital data file corresponding to a speech take into a set of data that is representative of text;
(f) subsequent to said implementing, creating a file identifier which is derived from said set of data and associating said file identifier with said digital data file; and
(g) subsequent to said creating and associating, storing said digital data file and the associated file identifier on a storage medium, thereby facilitating accessing of said digital data file.
1 Assignment
0 Petitions
Accused Products
Abstract
A method of labelling digital audio data corresponding to recorded audio ("takes"). According to this method speech recognition software is employed to generate text based on a portion of the recorded audio data. The generated text is then associated with the audio data file, thereby labelling the file based on its content. According to this technique, the need for monitoring and manual entry of text data in labelling takes is eliminated.
28 Citations
5 Claims
-
1. A method of automatically labeling takes in an audio editing system comprising:
-
(a) providing a workstation having memory means and a processor unit associated therewith; (b) programming said workstation with operating system software; (c) accessing with said workstation a digital data file corresponding to a speech take; (d) interfacing said system software with speech recognition software; (e) subsequent to said interfacing and said accessing, implementing said speech recognition software to translate at least a portion of said digital data file corresponding to a speech take into a set of data that is representative of text; (f) subsequent to said implementing, creating a file identifier which is derived from said set of data and associating said file identifier with said digital data file; and (g) subsequent to said creating and associating, storing said digital data file and the associated file identifier on a storage medium, thereby facilitating accessing of said digital data file. - View Dependent Claims (2, 3, 4, 5)
-
Specification