8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Non-Audible Murmur Recognition

Yoshitaka Nakajima (1), Hideki Kashioka (1), Kiyohiro Shikano (1), Nick Campbell (2)

(1) Nara Institute of Science and Technology, Japan
(2) ATR-HIS, Japan

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. Additionally we propose laryngeal elevation index (LEI), a new index of prosody, which can show the prosody of NAM without F0, using simple processing of images from medical ultrasonography. We realized and defined NAM never used for input or communication and propose that we should make use of it for the interface of human-human and human-cybernetic machines.

Full Paper

Bibliographic reference.  Nakajima, Yoshitaka / Kashioka, Hideki / Shikano, Kiyohiro / Campbell, Nick (2003): "Non-audible murmur recognition", In EUROSPEECH-2003, 2601-2604.