Standard
Feature extraction for speech and music discrimination. / Zhou, Huiyu; Sadka, Abdul
; Jiang, Richard M. 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings. IEEE, 2008. p. 170-173 4564943 (2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Zhou, H, Sadka, A
& Jiang, RM 2008,
Feature extraction for speech and music discrimination. in
2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings., 4564943, 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings, IEEE, pp. 170-173, 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, London, United Kingdom,
18/06/08.
https://doi.org/10.1109/CBMI.2008.4564943APA
Vancouver
Zhou H, Sadka A
, Jiang RM.
Feature extraction for speech and music discrimination. In 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings. IEEE. 2008. p. 170-173. 4564943. (2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings). doi: 10.1109/CBMI.2008.4564943
Author
Bibtex
@inproceedings{5b2391cb64dd4599afba2563bf966fdd,
title = "Feature extraction for speech and music discrimination",
abstract = "Driven by the demand of information retrieval, video editing and human-computer interface, in this paper we propose a novel spectral feature for music and speech discrimination. This scheme attempts to simulate a biological model using the averaged cepstrum, where human perception tends to pick up the areas of large cepstral changes. The cepstrum data that is away from the mean value will be exponentially reduced in magnitude. We conduct experiments of music/speech discrimination by comparing the performance of the proposed feature with that of previously proposed features in classification. The dynamic time warping based classification verifies that the proposed feature has the best quality of music/speech classification in the test database.",
author = "Huiyu Zhou and Abdul Sadka and Jiang, {Richard M.}",
year = "2008",
month = sep,
day = "22",
doi = "10.1109/CBMI.2008.4564943",
language = "English",
isbn = "9781424420445",
series = "2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings",
publisher = "IEEE",
pages = "170--173",
booktitle = "2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings",
note = "2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008 ; Conference date: 18-06-2008 Through 20-06-2008",
}
RIS
TY - GEN
T1 - Feature extraction for speech and music discrimination
AU - Zhou, Huiyu
AU - Sadka, Abdul
AU - Jiang, Richard M.
PY - 2008/9/22
Y1 - 2008/9/22
N2 - Driven by the demand of information retrieval, video editing and human-computer interface, in this paper we propose a novel spectral feature for music and speech discrimination. This scheme attempts to simulate a biological model using the averaged cepstrum, where human perception tends to pick up the areas of large cepstral changes. The cepstrum data that is away from the mean value will be exponentially reduced in magnitude. We conduct experiments of music/speech discrimination by comparing the performance of the proposed feature with that of previously proposed features in classification. The dynamic time warping based classification verifies that the proposed feature has the best quality of music/speech classification in the test database.
AB - Driven by the demand of information retrieval, video editing and human-computer interface, in this paper we propose a novel spectral feature for music and speech discrimination. This scheme attempts to simulate a biological model using the averaged cepstrum, where human perception tends to pick up the areas of large cepstral changes. The cepstrum data that is away from the mean value will be exponentially reduced in magnitude. We conduct experiments of music/speech discrimination by comparing the performance of the proposed feature with that of previously proposed features in classification. The dynamic time warping based classification verifies that the proposed feature has the best quality of music/speech classification in the test database.
U2 - 10.1109/CBMI.2008.4564943
DO - 10.1109/CBMI.2008.4564943
M3 - Conference contribution/Paper
AN - SCOPUS:51849119720
SN - 9781424420445
T3 - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings
SP - 170
EP - 173
BT - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings
PB - IEEE
T2 - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008
Y2 - 18 June 2008 through 20 June 2008
ER -
