This paper presents a method for noisy speech enhancement based on integration of a formant-tracking linear prediction (FTLP) model of spectral envelope and a harmonic noise model (HNM) of the excitation of speech. The time-varying trajectories of the parameters of the LP and HNM models are tracked with Viterbi classifiers and smoothed with Kalman filters. A frequency domain pitch estimation is proposed, that searches for the peak SNRs at the harmonics. The LP-HNM model is used to deconstruct noisy speech, de-noise its LP and HNM models and then reconstitute cleaned speech. Experimental evaluations show the performance gains resulting from the formant tracking, harmonic extraction and noise reduction stages.
|Publication status||Published - Sep 2006|
|Event||14th European Signal Processing Conference - Florence, Italy|
Duration: 4 Sep 2006 → 8 Sep 2006
|Conference||14th European Signal Processing Conference|
|Abbreviated title||EUSIPCO 2006|
|Period||4/09/06 → 8/09/06|