A Probabilistic Approach For Phase Estimation in Single-Channel Speech Enhancement Using Von Mises Phase Priors

TitleA Probabilistic Approach For Phase Estimation in Single-Channel Speech Enhancement Using Von Mises Phase Priors
Publication TypeConference Paper
Year of Publication2014
AuthorsKulmer, J., Mowlaee P., & Watanabe M.
Conference NameIEEE Workshop on Machine Learning for Signal Processing
Date PublishedSept.
Abstract

In many artificial intelligence systems human voice is considered as the medium for information transmission. Human-machine communication by voice becomes difficult when speech is mixed with some background noise. As a remedy, a single-channel speech enhancement is indispensable for reducing background noise from noisy speech to make it suitable for automatic speech recognition and telephony speech. While the conventional techniques for single-channel speech enhancement incorporate noisy phase in both amplitude estimation and signal reconstruction stages, in this paper we propose a probabilistic method to estimate the clean speech phase from noisy observation. Our proposed method consists of phase unwrapping followed by threshold-based temporal smoothing using von Mises phase priors. The proposed phase enhancement method leads to improved speech quality and intelligibility predicted by instrumental measures without explicit incorporation of amplitude enhancement.

 

URLhttps://ieeexplore.ieee.org/document/6958861/
Citation KeyMLSP2014
SPSC cross-references