Non-target speech identification method for speech recognition and audio indexing system, uses transcription of non-target speech expressions within audio stream using transcription system

摘要

The non-target speech identification method uses transcription of each non-target speech expression within an audio stream using a transcription system which is trained via the target speech, with generation of a confidence weighting for each transcribed speech expression and identification of the speech expression as a non-target speech expression when the confidence weighting fails to meet defined criteria. Also included are Independent claims for the following; (a) a non-target speech identification system; (b) a product for non-target speech identification