Online Monaural Speech Enhancement Based on Periodicity Analysis and A Priori SNR Estimation

TL;DR

This paper introduces an online monaural speech enhancement algorithm that utilizes a novel phase-corrected filterbank and a periodicity degree feature for robust noise suppression and fundamental period detection.

Contribution

It proposes a new periodicity degree feature and a phase-corrected filterbank for improved real-time speech enhancement and pitch detection in noisy environments.

Findings

The algorithm achieves high P0 detection accuracy across different corpora.

It outperforms or matches state-of-the-art algorithms in various noise conditions.

The method is effective in non-stationary noise environments.

Abstract

This paper describes an online algorithm for enhancing monaural noisy speech. Firstly, a novel phase-corrected low-delay gammatone filterbank is derived for signal subband decomposition and resynthesis; the subband signals are then analyzed frame by frame. Secondly, a novel feature named periodicity degree (PD) is proposed to be used for detecting and estimating the fundamental period (P0) in each frame and for estimating the signal-to-noise ratio (SNR) in each frame-subband signal unit. The PD is calculated in each unit as the multiplication of the normalized autocorrelation and the comb filter ratio, and shown to be robust in various low-SNR conditions. Thirdly, the noise energy level in each signal unit is estimated recursively based on the estimated SNR for units with high PD and based on the noisy signal energy level for units with low PD. Then the a priori SNR is estimated using a decision-directed approach with the estimated noise level. Finally, a revised Wiener gain is calculated, smoothed, and applied to each unit; the processed units are summed across subbands and frames to form the enhanced signal. The P0 detection accuracy of the algorithm was evaluated on two corpora and showed comparable performance on one corpus and better performance on the other corpus when compared to a recently published pitch detection algorithm. The speech enhancement effect of the algorithm was evaluated on one corpus with two objective criteria and showed better performance in one highly non-stationary noise and comparable performance in two other noises when compared to a state-of-the-art statistical-model based algorithm.