Share Email Print

Proceedings Paper

Development and testing of an audio forensic software for enhancing speech signals masked by loud music
Author(s): Robert A. Dobre; Cristian Negrescu; Dumitru Stanomir
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In many situations audio recordings can decide the fate of a trial when accepted as evidence. But until they can be taken into account they must be authenticated at first, but also the quality of the targeted content (speech in most cases) must be good enough to remove any doubt. In this scope two main directions of multimedia forensics come into play: content authentication and noise reduction. This paper presents an application that is included in the latter. If someone would like to conceal their conversation, the easiest way to do it would be to turn loud the nearest audio system. In this situation, if a microphone was placed close by, the recorded signal would be apparently useless because the speech signal would be masked by the loud music signal. The paper proposes an adaptive filters based solution to remove the musical content from a previously described signal mixture in order to recover the masked vocal signal. Two adaptive filtering algorithms were tested in the proposed solution: the Normalised Least Mean Squares (NLMS) and Recursive Least Squares (RLS). Their performances in the described situation were evaluated using Simulink, compared and included in the paper.

Paper Details

Date Published: 14 December 2016
PDF: 7 pages
Proc. SPIE 10010, Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies VIII, 100103A (14 December 2016); doi: 10.1117/12.2243356
Show Author Affiliations
Robert A. Dobre, Politehnica Univ. of Bucharest (Romania)
Cristian Negrescu, Politehnica Univ. of Bucharest (Romania)
Dumitru Stanomir, Politehnica Univ. of Bucharest (Romania)

Published in SPIE Proceedings Vol. 10010:
Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies VIII
Marian Vladescu; Cornel T. Panait; Razvan Tamas; George Caruntu; Ionica Cristea, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?