Using a loudness-level-reference segment of audio to normalize relative audio levels among different audio files when combining content of the audio files

摘要

The present invention records a loudness-level-reference segment of audio when creating speech audio files and audio files including background sounds. The speech audio files can then be combined with the background sound containing audio files in any desirable combination. When combining the files, the relative audio level of the files is matched, by matching the loudness-level-reference segments with each other. Any of a variety of known digital signal processing techniques can be used to normalize the component audio files. The combined audio files containing speech and background sounds (e.g. ambient noise) having matching relative audio levels can be used to test and/or train a speech recognition engine or a speech processing system.