Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Speech Enhancement Based on Discrete Wavelet Packet Transform and Itakura-Saito Nonnegative Matrix Factorisation

Liu Houguang, Wang Wenbo, Xue Lin, Yang Jianhua, Wang Zhihua, Hua Chunli

Archives of Acoustics

2020

Vol. 45, No. 4

565--572

Nonnegative matrix factorization (NMF) is one of the most popular machine learning tools for speech enhancement (SE). However, there are two problems reducing the performance of the traditional NMF-based SE algorithms. One is related to the overlap-and-add operation used in the short time Fourier transform (STFT) based signal reconstruction, and the other is the Euclidean distance used commonly as an objective function; these methods can cause distortion in the SE process. In order to get over these shortcomings, we propose a novel SE joint framework which combines the discrete wavelet packet transform (DWPT) and the Itakura-Saito nonnegative matrix factorisation (ISNMF). In this approach, the speech signal was first split into a series of subband signals using the DWPT. Then, the ISNMF was used to enhance the speech for each subband signal. Finally, the inverse DWPT (IDWT) was utilised to reconstruct these enhanced speech subband signals. The experimental results show that the proposed joint framework effectively enhances the performance of speech enhancement and performs better in the unseen noise case compared to the traditional NMF methods.

Influence of middle ear disorder in round-window stimulation using a finite element human ear model

Zhou Kai, Liu Houguang, Yang Jianhua, Zhao Yu, Rao Zhushi, Yang Shanguo

Acta of Bioengineering and Biomechanics

2019

Vol. 21, no. 1

3--12

The aim of this work was to study the effect of middle ear disorder on round window (RW) stimulation, so as to provide references for the optimal design of RW stimulation type middle ear implants (MEIs). Methods: A human ear finite-element model was built by reverse engineering technique based on micro-computed tomography scanning images of human temporal bone, and was validated by three sets of comparisons with experimental data. Then, based on this model, typical disorders in otosclerosis and otitis media were simulated. Finally, their influences on the RW stimulation were analyzed by comparison of the displacements of the basilar membrane. Results: For the otosclerosis, the stapedial abnormal bone growth severely deteriorated the equivalent sound pressure of the RW stimulation at higher frequencies, while the hardening of ligaments and tendons prominently decreased the RW stimulation at lower frequencies. Besides, among the hardening of the studied tissues, the influence of the stapedial annular ligament’s hardening was much more significant. For the otitis media, the round window membrane (RWM)’s thickening mainly decreased the RW stimulation’s performance at lower frequencies. When the elastic modulus’ reduction of the RWM was considered at the same time especially for the acute otitis media, it would raise the lower-frequency performance of the RW stimulation. Conclusions: The influence of the middle ear disorder on the RW stimulation is considerable and variable, it should be considered during the design of the RW stimulation type MEIs.