scispace - formally typeset
M

Michael Savic

Researcher at Rensselaer Polytechnic Institute

Publications -  12
Citations -  505

Michael Savic is an academic researcher from Rensselaer Polytechnic Institute. The author has contributed to research in topics: Signal & Voice activity detection. The author has an hindex of 8, co-authored 12 publications receiving 501 citations. Previous affiliations of Michael Savic include The Walt Disney Company.

Papers
More filters
PatentDOI

Speech transformation system

TL;DR: In this paper, a high quality voice transformation system and method operates during a training mode to store voice signal characteristics representing target and source voices, and then during a real time transformation mode, a signal representing source speech is segmented into overlapping segments, analyzed to separate the excitation spectrum from the tone quality spectrum.
Patent

Detection of leaks in pipelines

TL;DR: In this paper, an apparatus and process for determining the existence and location of a leak in an underground pipe, comprises a plurality of remote acoustic transmission sensor units distributed along the pipe and each containing equipment for analyzing acoustic signals from the pipe.
Patent

Detection of leaks in vessels

TL;DR: An apparatus and process for determining the existence and location of a leak in a vessel such as a container or an above ground or underground pipe, comprises a plurality of remote acoustic transmission sensor units distributed along the pipe and each containing equipment for analyzing acoustic signals from the pipe as mentioned in this paper.
PatentDOI

Detection of cholesterol deposits in arteries

TL;DR: In this article, a method of diagnosing arterial stenosis from a received Doppler shifted acoustic signal from an artery during multiple heartbeats, each having systolic and diastolic phases, using pattern recognition techniques that are applied to the signal to determine the presence of turbulence during the dilation phase, which indicates stenosis.
Patent

Monitoring pressurized vessels for leaks, ruptures or hard hits

TL;DR: In this paper, the authors use a transducers attached to a vessel and transmit acoustic signals which are processed to extract frequency spectra which contain dominant resonant frequency peaks, if the vessel contains a small leak or rupture.