TY - GEN
T1 - A novel NMF-HMM speech enhancement algorithm based on Poisson mixture model
AU - Xiang, Yang
AU - Shi, Liming
AU - Lisby Højvang, Jesper
AU - Højfeldt Rasmussen, Morten
AU - Christensen, Mads Græsbøll
PY - 2021/6/11
Y1 - 2021/6/11
N2 - In this paper, we propose a novel non-negative matrix factorization (NMF) and hidden Markov model (NMF-HMM) based speech enhancement algorithm, which employs a Poisson mixture model (PMM). {Compared to} the previously proposed NMF-HMM method, the new algorithm, termed PMM-NMF-HMM, {uses} the Poisson mixture distribution for the state conditional likelihood function for a HMM rather than the single Poisson distribution. {This means that there are the more basis matrices that can be used to model the speech and noise signals, so more signal information can be captured by the resulting model. The proposed method is supervised and thus includes a training and an enhancement stage. It is shown that, in the training stage, the proposed method can be implemented efficiently using multiplicative update (MU) for the model parameters, much like the NMF-HMM algorithm. In the speech enhancement stage, which can be performed online, a novel PMM-NMF-HMM minimum mean-square error (MMSE) estimator is developed. The experimental results indicate that the PMM-NMF-HMM method can obtain higher short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) score than NMF-HMM. Additionally, the {method also outperforms other state-of-the-art NMF-based supervised speech enhancement algorithms.
AB - In this paper, we propose a novel non-negative matrix factorization (NMF) and hidden Markov model (NMF-HMM) based speech enhancement algorithm, which employs a Poisson mixture model (PMM). {Compared to} the previously proposed NMF-HMM method, the new algorithm, termed PMM-NMF-HMM, {uses} the Poisson mixture distribution for the state conditional likelihood function for a HMM rather than the single Poisson distribution. {This means that there are the more basis matrices that can be used to model the speech and noise signals, so more signal information can be captured by the resulting model. The proposed method is supervised and thus includes a training and an enhancement stage. It is shown that, in the training stage, the proposed method can be implemented efficiently using multiplicative update (MU) for the model parameters, much like the NMF-HMM algorithm. In the speech enhancement stage, which can be performed online, a novel PMM-NMF-HMM minimum mean-square error (MMSE) estimator is developed. The experimental results indicate that the PMM-NMF-HMM method can obtain higher short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ) score than NMF-HMM. Additionally, the {method also outperforms other state-of-the-art NMF-based supervised speech enhancement algorithms.
KW - Hidden Markov model (HMM)
KW - Minimum mean-square error (MMSE)
KW - Non-negative matrix factorization (NMF)
KW - Poisson mixture model (PMM)
KW - Speech enhancement
UR - http://www.scopus.com/inward/record.url?scp=85115136673&partnerID=8YFLogxK
U2 - 10.1109/ICASSP39728.2021.9414620
DO - 10.1109/ICASSP39728.2021.9414620
M3 - Article in proceeding
SN - 978-1-7281-7606-2
T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
SP - 721
EP - 725
BT - ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
T2 - ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Y2 - 6 June 2021 through 11 June 2021
ER -