We propose a new style of practical input interface for the recognition of non-audible murmur (NAM), i.e., for the recognition of inaudible speech produced without vibration of the vocal folds. We developed a microphone attachment, which adheres to the skin, applying the principle of a medical stethoscope, found the ideal position for sampling flesh-conducted NAM sound vibration and retrained an acoustic model with NAM samples. Then using the Julius Japanese Dictation Toolkit, we tested the possibilities for practical use of this method in place of an external microphone for analyzing air-conducted voice sound.
展开▼
