Abstract
Online multi-microphone speech enhancement aims to extract target speech from multiple noisy inputs by exploiting the spatial information as well as the spectro-temporal characteristics with low latency. Acoustic parameters such as the acoustic transfer function and speech and noise spatial covariance matrices (SCMs) should be estimated in a causal manner to enable the online estimation of the clean speech spectra. In this paper, we propose an improved estimator for the speech SCM, which can be parameterized with the speech power spectral density (PSD) and relative transfer function (RTF). Specifically, we adopt the temporal cepstrum smoothing (TCS) scheme to estimate the speech PSD, which is conventionally estimated with temporal smoothing. Furthermore, we propose a novel RTF estimator based on a time difference of arrival (TDoA) estimate obtained by the cross-correlation method. Furthermore, we propose refining the initial estimate of speech SCM by utilizing the estimates for the clean speech spectrum and clean speech power spectrum. The proposed approach showed superior performance in terms of the perceptual evaluation of speech quality (PESQ) scores, extended short-time objective intelligibility (eSTOI), and scale-invariant signal-to-distortion ratio (SISDR) in our experiments on the CHiME-4 database.
Funder
National Research Foundation of Korea
Institute for Information and Communications Technology Promotion
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference62 articles.
1. Vary, P., and Martin, R. (2006). Digital Speech Transmission: Enhancement, Coding and Error Concealment, John Wiley & Sons.
2. Kates, J.M. (2008). Digital Hearing Aids, Plural Publishing.
3. Rabiner, L., and Juang, B.H. (1993). Fundamentals of Speech Recognition, Prentice-Hall, Inc.
4. Improved Speech Enhancement Considering Speech PSD Uncertainty;Kim;IEEE/ACM Trans. Audio Speech Lang. Process.,2022
5. iDeepMMSE: An improved deep learning approach to MMSE speech and noise power spectrum estimation for speech enhancement;Kim;Proc. Interspeech,2022