Real-Time Speech Separation by Semi-supervised Nonnegative Matrix Factorization
نویسندگان
چکیده
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 nonstationary noise show that this system performs as well as a supervised NMF algorithm exploiting noise components learned from the same noise environment as the test sample. Furthermore, it outperforms a supervised system trained on different noise conditions.
منابع مشابه
Blind Speech Separation with GCC-NMF
We introduce a blind source separation algorithm named GCCNMF that combines unsupervised dictionary learning via nonnegative matrix factorization (NMF) with spatial localization via the generalized cross correlation (GCC) method. Dictionary learning is performed on the mixture signal, with separation subsequently achieved by grouping dictionary atoms, over time, according to their spatial origi...
متن کاملOnline PLCA for Real-Time Semi-supervised Source Separation
Non-negative spectrogram factorization algorithms such as probabilistic latent component analysis (PLCA) have been shown to be quite powerful for source separation. When training data for all of the sources are available, it is trivial to learn their dictionaries beforehand and perform supervised source separation in an online fashion. However, in many real-world scenarios (e.g. speech denoisin...
متن کاملA Modified Digital Image Watermarking Scheme Based on Nonnegative Matrix Factorization
This paper presents a modified digital image watermarking method based on nonnegative matrix factorization. Firstly, host image is factorized to the product of three nonnegative matrices. Then, the centric matrix is transferred to discrete cosine transform domain. Watermark is embedded in low frequency band of this matrix and next, the reverse of the transform is computed. Finally, watermarked ...
متن کاملRegularized nonnegative matrix factorization using Gaussian mixture priors for supervised single channel source separation
We introduce a new regularized nonnegative matrix factorization (NMF) method for supervised single-channel source separation (SCSS). We propose a new multi-objective cost function which includes the conventional divergence term for the NMF together with a prior likelihood term. The first term measures the divergence between the observed data and the multiplication of basis and gains matrices. T...
متن کاملStatistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervised approach requires a very large amount of pair data for training, it is not...
متن کامل