By Topic

Statistical approaches to enhancement of body-conducted speech detected with non-audible murmur microphone

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Tomoki Toda ; Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma-shi, 630-0192, Japan

In this paper, we review our recent research on technologies for enhancing body-conducted speech detected with nonaudible murmur (NAM) microphone. NAM microphone has been developed to detect an extremely soft whispered voice, which is useful for silent speech communication. Moreover, it is also capable of detecting other voices such as a soft voice and a normal voice while effectively reducing external noise owing to its noise-proof structure. On the other hand, speech quality of the detected voices severely degrades by the body-conductive recording. To address this issue, we have developed technologies for statistically converting body-conducted speech into normal speech. This paper gives an overview of these technologies and a further attempt to make it possible to use them for human-to-human speech communication.

Published in:

Complex Medical Engineering (CME), 2012 ICME International Conference on

Date of Conference:

1-4 July 2012