Bu öğeden alıntı yapmak, öğeye bağlanmak için bu tanımlayıcıyı kullanınız:
http://hdl.handle.net/11452/25397
Başlık: | Regularized all-pole models for speaker verification under noisy environments |
Yazarlar: | Kinnunen, Tomi Saeidi, Rahim Pohjalainen, Jouni Alku, Paavo Uludağ Üniversitesi/Mühendislik-Mimarlık Fakültesi/Elektronik Mühendisliği Bölümü. Hanilçi, Cemal Ertaş, Figen S-4967-2016 AAH-4188-2021 |
Anahtar kelimeler: | Engineering Speaker verification Spectrum estimation Linear prediction Regularized linear prediction |
Yayın Tarihi: | Mar-2012 |
Yayıncı: | IEEE |
Atıf: | Hanilçi, C. vd. (2012). "Regularized all-pole models for speaker verification under noisy environments". IEEE Signal Processing Letters, 19(3), 163-166. |
Özet: | Regularization of linear prediction based mel-frequency cepstral coefficient (MFCC) extraction in speaker verification is considered. Commonly, MFCCs are extracted from the discrete Fourier transform (DFT) spectrum of speech frames. In this paper, DFT spectrum estimate is replaced with the recently proposed regularized linear prediction (RLP) method. Regularization of temporally weighted variants, weighted LP (WLP) and stabilized WLP (SWLP) which have earlier shown success in speech and speaker recognition, is also introduced. A novel type of double autocorrelation (DAC) lag windowing is also proposed to enhance robustness. Experiments on the NIST 2002 corpus indicate that regularized all-pole methods (RLP, RWLP and RSWLP) yield large improvement on recognition accuracy under additive factory and babble noise conditions in terms of both equal error rate (EER) and minimum detection cost function (MinDCF). |
URI: | https://doi.org/10.1109/LSP.2012.2184284 https://ieeexplore.ieee.org/abstract/document/6130592 http://hdl.handle.net/11452/25397 |
ISSN: | 1070-9908 1558-2361 |
Koleksiyonlarda Görünür: | Web of Science |
Bu öğenin dosyaları:
Bu öğeyle ilişkili dosya bulunmamaktadır.
DSpace'deki bütün öğeler, aksi belirtilmedikçe, tüm hakları saklı tutulmak şartıyla telif hakkı ile korunmaktadır.