@inproceedings{3f2b81f41b8248faa4be48e6391b9ed4,
title = "An investigation of sub-band FM feature extraction in speaker recognition",
abstract = "Following recent evidence that FM features extracted from a sub-band decomposition of speech are highly uncorrelated, this paper investigates the effect of the number of auditory scale sub-bands in FM based front-end processing. For this study, a newly developed robust FM extraction method based on the least square differential ratio is used to extract features, comprising one FM component per sub-band. Automatic speaker recognition experiments were conducted on the cellular NIST 2001 database, with the number of filters in the front-end varied from 6 to 26. Performance degradation was observed for very low numbers of filters and very high numbers of filters. Results show that for a 4 kHz speech bandwidth, a minimum of 10 and a maximum of 18 sub-bands is a suitable choice for speech front-end applications such as automatic speaker recognition.",
keywords = "Automatic speaker recognition, Filter bank, Frequency modulation, Mel scale",
author = "T. Thiruvaran and J. Epps and E. Ambikairajah and E. Jones",
year = "2008",
doi = "10.1049/cp:20080634",
language = "English",
isbn = "9780863419317",
series = "IET Conference Publications",
number = "539 CP",
pages = "32--36",
booktitle = "IET Irish Signals and Systems Conference, ISSC 2008",
edition = "539 CP",
note = "IET Irish Signals and Systems Conference, ISSC 2008 ; Conference date: 18-06-2008 Through 19-06-2008",
}