Artificial bandwidth extension based on regularized piecewise linear mapping with discriminative region weighting and long-Span features
نویسندگان
چکیده
Artificial Bandwidth Extension (ABE) has been introduced to improve perceived speech quality and intelligibility of narrowband telephone speech. Most of the existing algorithms divided ABE into 2 sub-problems, namely extension of the excitation signal and that of the spectral envelope. In this paper, we propose a new method for spectral envelope extension based on REgularized piecewise linear mapping with DIscriminative region weighting And Long-span features (REDIAL). REDIAL is a revised version of SPLICE, a well-known method for speech enhancement. In REDIAL, however, discriminative model is introduced for space division step of the original SPLICE. The proposed REDIAL-based method approximates non-linear transformation from narrowband features to their wideband counterpart by a summation of piecewise linear transformations. The proposed method was compared with the widely used GMM-based method, through objective and subjective evaluations in both speaker-dependent and speaker-independent conditions. Both evaluations showed that the proposed method significantly outperforms the conventional GMM-based method.
منابع مشابه
Quantitative Structure-Activity Relationship Study on Thiosemicarbazone Derivatives as Antitubercular agents Using Artificial Neural Network and Multiple Linear Regression
Background and purpose: Nonlinear analysis methods for quantitative structure–activity relationship (QSAR) studies better describe molecular behaviors, than linear analysis. Artificial neural networks are mathematical models and algorithms which imitate the information process and learning of human brain. Some S-alkyl derivatives of thiosemicarbazone are shown to be beneficial in prevention and...
متن کاملLinXGBoost: Extension of XGBoost to Generalized Local Linear Models
XGBoost is often presented as the algorithm that wins every ML competition. Surprisingly, this is true even though predictions are piecewise constant. This might be justified in high dimensional input spaces, but when the number of features is low, a piecewise linear model is likely to perform better. XGBoost was extended into LinXGBoost that stores at each leaf a linear model. This extension, ...
متن کاملStructured and Inûnite DiscriminativeModels for Speech Recognition
In continuous speech recognition, observations are sequential data with variable length, and labels are sequence of words (or sub-words) possibly having unbounded number of classes. It is thus impractical to robustly construct models for thewholeword sequence. To address this problem, rather than treating the whole sentence as an atomic unit, structure needs to be introduced into classiûers to ...
متن کاملLong Span Features and Minimum Phoneme Error Heteroscedastic Linear Discriminant Analysis
In this paper we explore the effect of long-span features, resulting from concatenating multiple speech frames and projecting the resulting vector onto a subspace using Linear Discriminant Analysis (LDA) techniques. We show that LDA is not always effective in selecting the optimal combination of long-span features, and introduce a discriminative feature analysis method that seeks to minimize ph...
متن کاملPlanelet Transform: A New Geometrical Wavelet for Compression of Kinect-like Depth Images
With the advent of cheap indoor RGB-D sensors, proper representation of piecewise planar depth images is crucial toward an effective compression method. Although there exist geometrical wavelets for optimal representation of piecewise constant and piecewise linear images (i.e. wedgelets and platelets), an adaptation to piecewise linear fractional functions which correspond to depth variation ov...
متن کامل