Least 1-Norm Pole-Zero Modeling with Sparse Deconvolution for Speech Analysis

Publikation: Forskning - peer reviewKonferenceartikel i tidsskrift

Abstrakt

In this paper, we present a speech analysis method based on sparse pole-zero modeling of speech. Instead of using the all-pole model to approximate the speech production filter, a pole-zero model is used for the combined effect of the vocal tract; radiation at the lips and the glottal pulse shape. Moreover, to consider the spiky excitation form of the pulse train during voiced speech, the modeling parame- ters and sparse residuals are estimated in an iterative fashion using a least 1-norm pole-zero with sparse deconvolution algorithm. Com- pared with the conventional two-stage least squares pole-zero, linear prediction and sparse linear prediction methods, experimental results show that the proposed speech analysis method has lower spectral distortion, higher reconstruction SNR and sparser residuals.
Luk

Detaljer

In this paper, we present a speech analysis method based on sparse pole-zero modeling of speech. Instead of using the all-pole model to approximate the speech production filter, a pole-zero model is used for the combined effect of the vocal tract; radiation at the lips and the glottal pulse shape. Moreover, to consider the spiky excitation form of the pulse train during voiced speech, the modeling parame- ters and sparse residuals are estimated in an iterative fashion using a least 1-norm pole-zero with sparse deconvolution algorithm. Com- pared with the conventional two-stage least squares pole-zero, linear prediction and sparse linear prediction methods, experimental results show that the proposed speech analysis method has lower spectral distortion, higher reconstruction SNR and sparser residuals.
OriginalsprogEngelsk
Artikelnummer10.1109/ICASSP.2017.7952252
TidsskriftI E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
Sider (fra-til)731-735
Antal sider5
ISSN1520-6149
StatusUdgivet - 19 jun. 2017
Begivenhed - New Orleans, USA

Konference

KonferenceThe 42nd IEEE International Conference on Acoustics, Speech and Signal Processing
LandUSA
ByNew Orleans
Periode05/03/201709/03/2017
Internetadresse

Kort

ID: 245960883