Amplitude and Phase Information Interaction for Speech Enhancement Method
نویسندگان
چکیده
In order to improve the speech enhancement ability of FullSubNet model, an improved method FullSubNet-pMix is proposed. Specifically, pMix module added structure full-band frequency domain information processing, which realizes interaction between amplitude spectrum and phase spectrum. At same time, hyperparameters used in training are optimized so that sub-band system can play a better role. Experiments carried out on selected test sets. The experimental results show proposed independently effect four evaluation indicators WB-PESQ, NB-PESQ, STOI, SI-SDR than original model. Therefore, this paper effectively enhance model extract use voice information. impact different loss functions performance was also verified.
منابع مشابه
A speech enhancement method by coupling speech detection and spectral amplitude estimation
In this paper, a single-channel speech enhancement method by coupling speech detection and spectral amplitude estimation is proposed. First, the optimal detector used for the spectral coefficients of the speech signal is obtained by minimizing the combined risk function which considers both detection and estimation errors. Second, according to the optimal speech detector, the optimal spectral a...
متن کاملShow & Tell: Iterative Refinement of Amplitude and Phase in Single-channel Speech Enhancement
While the state-of-the-art speech enhancement methods are focused on the modification of the noisy spectral amplitude, our recent findings demonstrate positive impact of incorporating the speech phase spectrum in speech enhancement. In this show and tell proposal, we demonstrate the recent progress towards utilizing the phase information in closed-loop iterative manner leading to the joint enha...
متن کاملDistributed multichannel speech enhancement with minimum mean-square error short-time spectral amplitude, log-spectral amplitude, and spectral phase estimation
In this paper, the authors present optimal multichannel frequency domain estimators for minimum mean-square error (MMSE) short-time spectral amplitude (STSA), log-spectral amplitude (LSA), and spectral phase estimation in a widely distributed microphone configuration. The estimators utilize Rayleigh and Gaussian statistical models for the speech prior and noise likelihood with a diffuse noise f...
متن کاملIterative refinement of amplitude and phase in single-channel speech enhancement
While the state-of-the-art speech enhancement methods are focused on the modification of the noisy spectral amplitude, our recent findings demonstrate positive impact of incorporating the speech phase spectrum in speech enhancement. In this show and tell proposal, we demonstrate the recent progress towards utilizing the phase information in closed-loop iterative manner leading to the joint enha...
متن کاملMicrophone Array Speech Enhancement by Bayesian Estimation of Spectral Amplitude and Phase
Microphone arrays provide new opportunities for noise reduction and speech enhancement. This paper presents a novel decomposition of the estimation problems for short-time spectral amplitude (STSA), log STSA, and phase in the Bayesian estimation framework. The decomposition is based on the notion of sufficient statistics for the microphone array case. It nicely generalizes the wellknown single-...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied sciences
سال: 2023
ISSN: ['2076-3417']
DOI: https://doi.org/10.3390/app13148025