Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Bing-yin Xia"'
Autor:
Changchun Bao, Bing-yin Xia
Publikováno v:
Speech Communication. 60:13-29
A novel speech enhancement method based on Weighted Denoising Auto-encoder (WDA) and noise classification is proposed in this paper. A weighted reconstruction loss function is introduced into the conventional Denoising Auto-encoder (DA), and the rela
Publikováno v:
Speech Communication. 52:710-724
In this paper, an efficient transcoding algorithm between AMR-NB and G.729ab is proposed. The proposed algorithm further elaborates on solutions when a DTX function is adopted between the source and destination coding systems. When neither, either or
Publikováno v:
IIH-MSP
Existing speech enhancement methods can improve speech quality but not speech intelligibility, especially in low SNR conditions. To solve this problem, an algorithm for improving speech intelligibility using the Constraints on Speech Distortion and N
Publikováno v:
ChinaSIP
This paper presents a novel speech enhancement algorithm based on β-order GARCH (Generalized Auto-regressive Conditional Heteroscedasticity) model. The speech signal is modeled as β-order GARCH process, and the a priori SNR is estimated effectively
Publikováno v:
ChinaSIP
This paper proposes an adaptive β-order Minimum-Mean-Square-Error (MMSE) estimator for speech enhancement using super-Gaussian speech model (β-SG-MMSE). The spectral amplitude of clean speech is estimated by MMSE estimator under the assumption that
Autor:
Bing-yin Xia, Changchun Bao
Publikováno v:
2012 IEEE 11th International Conference on Signal Processing.
In order to integrate the characteristics of different noise reduction algorithms, a wavelet fusion method for speech enhancement is proposed in this paper. In the proposed method, the noisy speech is first decomposed into several sub-bands by wavele
Publikováno v:
2012 IEEE 11th International Conference on Signal Processing.
In this paper, an improved phase-error based filter (IPBF) for dual-microphone noise reduction is proposed. First, instead of the Wiener filter, a statistical-model-based amplitude estimator is employed in IPBF algorithm to make further reduction of
Publikováno v:
TSP
An LP (Linear Prediction) spectrum modification method is proposed based on linear extrapolation for different signal to noise ratio under the white noise environment. A direct modification on the noisy LP spectrum is employed, since the autocorrelat
Publikováno v:
ISSPIT
In order to control the speech level automatically in the 3G mobile networks where Transcoder Free Operation (TrFO) is adopted, a compressed domain automatic level control (ALC) method is proposed based on ITU-T G.722.2 speech codec. The level of dec
Publikováno v:
ISSPIT
This paper proposes an improved β-order Weighted Euclidean Distortion Measure (I-β-WEDM) spectral estimator for speech enhancement. The new β-order WEDM gain function is introduced, in which a novel method of computing order β is proposed. In thi