TY - GEN
T1 - Maximum Likelihood Estimation of the Interference-Plus-Noise Cross Power Spectral Density Matrix for Own Voice Retrieval
AU - Hoang, Poul
AU - Tan, Zheng-Hua
AU - Lunner, Thomas
AU - Mark de Haan, Jan
AU - Jensen, Jesper
PY - 2020/5
Y1 - 2020/5
N2 - In headset and hearing aid applications, it is of interest to retrieve the user's own voice in a noisy environment, e.g. for telephony applications. To do so, the cross-power spectral density (CPSD) of the interference-plus-noise is required. In this paper, a novel maximum likelihood (ML) estimator of the interference-plus-noise CPSD matrix is proposed. The proposed method is able to estimate the interference-plus-noise CPSD matrix, even during signal regions with own voice activity. The method uses a novel procedure for estimating the interference-plus-noise CPSD matrix by first estimating the interference PSD and afterwards the noise PSD in a maximum likelihood sense. Simulation experiments, where the proposed method is compared to other noise CPSD matrix estimators, show that it performs on par or better than competing methods, particularly, in situation where the interferenceto-noise ratio is large.
AB - In headset and hearing aid applications, it is of interest to retrieve the user's own voice in a noisy environment, e.g. for telephony applications. To do so, the cross-power spectral density (CPSD) of the interference-plus-noise is required. In this paper, a novel maximum likelihood (ML) estimator of the interference-plus-noise CPSD matrix is proposed. The proposed method is able to estimate the interference-plus-noise CPSD matrix, even during signal regions with own voice activity. The method uses a novel procedure for estimating the interference-plus-noise CPSD matrix by first estimating the interference PSD and afterwards the noise PSD in a maximum likelihood sense. Simulation experiments, where the proposed method is compared to other noise CPSD matrix estimators, show that it performs on par or better than competing methods, particularly, in situation where the interferenceto-noise ratio is large.
KW - Own voice retrieval
KW - multi-microphone speech enhancement
KW - power spectral density estimation
UR - http://www.scopus.com/inward/record.url?scp=85089218505&partnerID=8YFLogxK
U2 - 10.1109/ICASSP40776.2020.9053988
DO - 10.1109/ICASSP40776.2020.9053988
M3 - Article in proceeding
SN - 978-1-5090-6632-2
T3 - International Conference on Acoustics Speech and Signal Processing (ICASSP)
SP - 6939
EP - 6943
BT - ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
T2 - ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Y2 - 4 May 2020 through 8 May 2020
ER -