Speech enhancement based on wavelet packet of an improved principal component analysis

A Bouzid, N Ellouze - Computer Speech & Language, 2016 - Elsevier
In this paper, we propose a single-channel speech enhancement method, based on the
combination of the wavelet packet transform and an improved version of the principal …

Signal subspace approach for psychoacoustically motivated speech enhancement

A Borowicz, A Petrovsky - Speech communication, 2011 - Elsevier
In this paper we deal with the perceptually motivated signal subspace methods for speech
enhancement. We focus on extended spectral-domain-constrained (SDC) estimator. It is …

Uniform and warped low delay filter-banks for speech enhancement

HW Löllmann, P Vary - Speech Communication, 2007 - Elsevier
A versatile filter-bank concept for adaptive subband filtering is proposed, which achieves a
significantly lower algorithmic signal delay than commonly used analysis–synthesis filter …

Косинусно-модулированные банки фильтров с фазовым преобразованием: реализация и применение в слуховых аппаратах

Рассмотрены вопросы построения цифровых слуховых аппаратов. В общем виде
описаны технические аспекты коррекции нарушений слуха. Большая часть материала …

Low delay filter-banks for speech and audio processing

HW Löllmann, P Vary - Speech and audio processing in adverse …, 2008 - Springer
Digital filter-banks are an integral part of many speech and audio processing algorithms
used in today's communication systems. They are commonly employed for adaptive …

Noisy speech enhancement with sparsity regularization

S Kammi, MRK Mollaei - Speech Communication, 2017 - Elsevier
In this paper, a novel unsupervised speech enhancement algorithm is proposed assuming
that both speech spectrogram and its temporal gradient are sparse. This assumption is …

An application of the warped discrete Fourier transform in the perceptual speech enhancement

A Borowicz, M Parfieniuk, AA Petrovsky - Speech communication, 2006 - Elsevier
An application of the warped discrete Fourier transform (WDFT) in the perceptual speech
enhancement is of interest. The WDFT allows nonuniform sampling the z-transform of finite …

Low-delay hearing aid based on cochlear model with nonuniform subband acoustic feedback cancellation

M Vashkevich, E Azarov… - 2012 Proceedings of the …, 2012 - ieeexplore.ieee.org
The paper presents a hearing aid (HA) system based on a low-delay cochlear filter bank
derived from the discrete cochlear model. The spectral gain shaping method (SGSM) that …

[HTML][HTML] Шумоподавление на основе перцептуальных алгоритмов спектрального вычитания и обработки сигналов в подпространствах

АА Петровский, ИС Азаров, ДС Лихачёв… - Речевые технологии …, 2012 - cyberleninka.ru
В данной статье оценивается эффективность алгоритмов шумоподавления,
основанных на спектральном вычитании и обработке сигнала в подпространствах …

Perceptually constrained subspace method for enhancing speech degraded by colored noise

A Borowicz, A Petrovsky - Audio Engineering Society Convention 118, 2005 - aes.org
In this paper we present a novel method for enhancing speech corrupted by colored noise. A
recent extension of signal subspace approach to colored-noise processes is employed …