Multi-Constraint Nonnegative Matrix Factorization Approach to Speech Enhancement with Nonstationary Noise
نویسندگان
چکیده
The enhancement of speech degraded by nonstationary noises and low signal-to-noise ratio (SNR) conditions is a high demanding but challenging task. We present a robust and effective single channel speech enhancement algorithm under the framework of Nonnegative Matrix Factorization (NMF). Considering the sparse property of speech and low-rank property of nonstationary noise, a new formulation for NMF based speech enhancement algorithm is proposed, in which we factorize the data matrix into two nonnegative sub-matrices with the constraints of speech sparsity and low rank of nonstationary noise to guarantee the effectiveness representation of the speech components from their corrupted version by nonstationary noise. As a result, a novel multi-constraint NMF speech enhancement (MC-NMFSE) algorithm is derived accordingly. Intensive experiments have been carried out to evaluate the performance of the MC-NMFSE algorithm and demonstrate its improvement against nonstationary noises.
منابع مشابه
A Projected Alternating Least square Approach for Computation of Nonnegative Matrix Factorization
Nonnegative matrix factorization (NMF) is a common method in data mining that have been used in different applications as a dimension reduction, classification or clustering method. Methods in alternating least square (ALS) approach usually used to solve this non-convex minimization problem. At each step of ALS algorithms two convex least square problems should be solved, which causes high com...
متن کاملReal-Time Speech Separation by Semi-supervised Nonnegative Matrix Factorization
In this paper, we present an on-line semi-supervised algorithm for real-time separation of speech and background noise. The proposed system is based on Nonnegative Matrix Factorization (NMF), where fixed speech bases are learned from training data whereas the noise components are estimated in real-time on the recent past. Experiments with spontaneous conversational speech and real-life nonstati...
متن کاملRegularized non-negative matrix factorization with temporal dependencies for speech denoising
We present a technique for denoising speech using temporally regularized nonnegative matrix factorization (NMF). In previous work [1], we used a regularized NMF update to impose structure within each audio frame. In this paper, we add frame-to-frame regularization across time and show that this additional regularization can also improve our speech denoising results. We evaluate our algorithm on...
متن کاملSpeech enhancement using convolutive nonnegative matrix factorization with cosparsity regularization
A novel method for speech enhancement based on Convolutive Non-negative Matrix Factorization (CNMF) is presented in this paper. The sparsity of activation matrix for speech components has already been utilized in NMF-based enhancement methods. However such methods do not usually take into account prior knowledge about occurrence relations between different speech components. By introducing the ...
متن کاملSpeech Enhancement Using Nonnegative MatrixFactorization and Hidden Markov Models
Reducing interference noise in a noisy speech recording has been a challenging task for many years yet has a variety of applications, for example, in handsfree mobile communications, in speech recognition, and in hearing aids. Traditional single-channel noise reduction schemes, such as Wiener filtering, do not work satisfactorily in the presence of non-stationary background noise. Alternatively...
متن کامل