Semi-Automatic Speech Transcription
First Claim
1. A method for providing semi-automatic speech transcription, comprising:
- (a) receiving audio by an automatic speech detection component;
(b) automatically detecting speech in the audio by the automatic speech detection component;
(c) providing by the automatic speech detection component the detected speech as a plurality of speech segments to a transcription tool;
(d) providing by the transcription tool each of the plurality of speech segments to a user via a transcription interface; and
(e) receiving by the transcription tool via the transcription interface an indication for each of the plurality of speech segments from the user, wherein the indication comprises a transcription of the speech segment or an indication of non-speech for the speech segments.
3 Assignments
0 Petitions
Accused Products
Abstract
A semi-automatic speech transcription system of the invention leverages the complementary capabilities of human and machine, building a system which combines automatic and manual approaches. With the invention, collected audio data is automatically distilled into speech segments, using signal processing and pattern recognition algorithms. The detected speech segments are presented to a human transcriber using a transcription tool with a streamlined transcription interface, requiring the transcriber to simply “listen and type”. This eliminates the need to manually navigate the audio, coupling the human effort to the amount of speech, rather than the amount of audio. Errors produced by the automatic system can be quickly identified by the human transcriber, which are used to improve the automatic system performance. The automatic system is tuned to maximize the human transcriber efficiency. The result is a system which takes considerably less time than purely manual transcription approaches to produce a complete transcription.
-
Citations
11 Claims
-
1. A method for providing semi-automatic speech transcription, comprising:
-
(a) receiving audio by an automatic speech detection component; (b) automatically detecting speech in the audio by the automatic speech detection component; (c) providing by the automatic speech detection component the detected speech as a plurality of speech segments to a transcription tool; (d) providing by the transcription tool each of the plurality of speech segments to a user via a transcription interface; and (e) receiving by the transcription tool via the transcription interface an indication for each of the plurality of speech segments from the user, wherein the indication comprises a transcription of the speech segment or an indication of non-speech for the speech segments. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A computer readable medium with program instructions for providing semi-automatic speech transcription, the program instructions executed by a computer, the instructions comprising:
-
(a) receiving audio by an automatic speech detection component; (b) automatically detecting speech in the audio by the automatic speech detection component; (c) providing by the automatic speech detection component the detected speech as a plurality of speech segments to a transcription tool; (d) providing by the transcription tool each of the plurality of speech segments to a user via a transcription interface; and (e) receiving by the transcription tool via the transcription interface an indication for each of the plurality of speech segments from the user, wherein the indication comprises a transcription of the speech segment or an indication of non-speech for the speech segments.
-
Specification