| CPC G10L 15/26 (2013.01) | 16 Claims |

|
8. A method comprising:
accessing, by a computing system, a plurality of transcripts, each generated from a different audio signal of a plurality of audio signals;
determining, by the computing system, an error rate for each of the plurality of transcripts;
determining, by a support vector machine application executing on the computing system and based on the error rate for each of the plurality of transcripts and subjective rankings of each of the plurality of transcripts, a plurality of objective categories, each corresponding to one of the subjective rankings and each associated with an error rate range, and wherein to determining the plurality of objective categories includes the support vector machine application selecting error rate boundaries between subjective rankings;
determining, by the computing system, an error rate for a new transcript of an audio signal not included in the plurality of audio signals; and
assigning, by the computing system, one of the objective categories to the new transcript based on the error rate for the new transcript.
|