AES New York 2015
Paper Session P21
P21 - Applications in Audio
Sunday, November 1, 10:00 am — 11:00 am (Room 1A07)
Chair:
Jason Corey, University of Michigan - Ann Arbor, MI, USA
P21-1 Loudness: A Function of Peak, RMS, and Mean Values of a Sound Signal—Hoda Nasereddin, IRIB University - Tehran, Iran; Ayoub Banoushi, IRIB University - Tehran, Iran
Every sound has a loudness recognized by hearing mechanism. Although loudness is a sensation measure, it is a function of sound signal properties. However, the function is not completely clear. In this paper we show that loudness determination as a function of effective mean square (RMS), peak, and average values of a sound signal is possible with an artificial neural network (ANN). We did not access to experimental data, so we produced required data using ITU-R BS.1770 model to train the network. The results show that the loudness can be simply estimated using sound signal physical features and without referring to complex hearing mechanism.
Convention Paper 9473 (Purchase now)
P21-2 Robust Audio Fingerprinting for Multimedia Recognition Applications—Sangmoon Lee, Samsung Electronics Co. Ltd. - Suwon, Gyeonggi-do, Korea; Inwoo Hwang, Samsung Electronics Co. Ltd. - Suwon-si, Gyeonggi-do, Korea; Byeong-Seob Ko, Samsung Electronics Co. Ltd. - Suwon, Korea; Kibeom Kim, Samsung Electronics Co. Ltd. - Suwon, Gyeonggi-do, Korea; Anant Baijal, Samsung Electronics Co. Ltd. - Suwon, Korea; Youngtae Kim, Samsung Electronics Co. Ltd. - Suwon, Gyeonggi-do, Korea
For a reliable audio fingerprinting (AFP) system for multimedia service, it is essential to make fingerprints robust to the time mismatch between live audio stream and prior recordings, as well as they should be sensitive to changes in contents for accurate discrimination. This paper presents a new AFP method using line spectral frequencies (LSFs), which are a kind of parameter that capture the underlying spectral shape: the proposed AFP method includes a new systematic scheme for the robust and discriminative fingerprint generation based on the inter-frame LSF difference and an efficient matching algorithm using the frame concentration measure based on the frame continuity property. The tests on databases containing a variety of advertisements are carried out to compare the performances of Phillips Robust Hash (PRH) and the proposed AFP. The test results demonstrate that the proposed AFP can maintain its true matched rate at over 98% even when the overlap ratio is as low as 87.5%. It can be concluded that the proposed AFP algorithm is more robust to time mismatch conditions when compared to PRH method.
Convention Paper 9475 (Purchase now)
