SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Izpis gradiva

Naslov:A noise robust feature extraction algorithm using joint wavelet packet subband decomposition and AR modeling of speech signals
Avtorji:Kotnik, Bojan (Avtor)
Kačič, Zdravko (Avtor)
Datoteke:URL http://dx.doi.org/10.1016/j.sigpro.2006.10.009
 
Jezik:Angleški jezik
Vrsta gradiva:Neznano ()
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
Opis:This paper presents a noise robust feature extraction algorithm NRFE using joint wavelet packet decomposition (WPD) and autoregressive (AR) modeling of a speech signal. In opposition to the short time Fourier transform (STFT)-based time-frequency signal representation, wavelet packet decomposition can lead to better representation of non-stationary parts of the speech signal (e.g. consonants). The vowels are well described with an AR model as in LPC analysis. The proposed Root-Log compression scheme is used to perform the computation of the wavelet packet parameters. The separately extracted WPD and AR-based parameters are combined together and then transformed with the usage of linear discriminant analysis (LDA) to finally produce a lower dimensional output feature vector. The noise robustness is improved with the application of proposed wavelet-based denoising algorithm with a modified soft thresholding procedure and time-frequency adaptive threshold. The proposed voice activity detector based on a skewness-to-kurtosis ratio of the LPC residual signal is used to effectively perform a frame-dropping principle. The speech recognition results achieved on Aurora 2 and Aurora 3 databases show overall performance improvement of 44.7% and 48.2% relative to the baseline MFCC front-end, respectively.
Ključne besede:automatic speech recognition, autoregressive modeling, modified soft thresholding, noise robust speech parameterization, wavelet packet decomposition
Leto izida:2007
UDK:621.39
URN:URN:SI:UM:DK:V5ZMGXBK
COBISS_ID:11170838 Povezava se odpre v novem oknu
ISSN pri članku:0165-1684
Število ogledov:1096
Število prenosov:24
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
Področja:Ostalo
:
  
Skupna ocena:(0 glasov)
Vaša ocena:Ocenjevanje je dovoljeno samo prijavljenim uporabnikom.
Objavi na:AddThis
AddThis uporablja piškotke, za katere potrebujemo vaše privoljenje.
Uredi privoljenje...

Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše podrobnosti ali sproži prenos.

Gradivo je del revije

Naslov:Signal processing
Skrajšan naslov:Signal process.
Založnik:North-Holland
ISSN:0165-1684
COBISS.SI-ID:26394368 Novo okno

Komentarji

Dodaj komentar

Za komentiranje se morate prijaviti.

Komentarji (0)
0 - 0 / 0
 
Ni komentarjev!

Nazaj
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici