This paper tries to fill the gap between Traditional Chinese Pulse Diagnosis (TCPD) and Doppler diagnosis by applying digital signal analysis and pattern classification techniques to wrist radial arterial Doppler bloo...
详细信息
A fast convergence speech enhancement method is proposed in this paper. The noise estimation acceleration technique is applied to the conventional statistical model based algorithm to shorten the convergence time afte...
详细信息
A fast convergence speech enhancement method is proposed in this paper. The noise estimation acceleration technique is applied to the conventional statistical model based algorithm to shorten the convergence time after the sudden change of noise intensity. First, the burst detection of power spectrum is performed on the noisy spectrum. Next, the loglikelihood ratio (LLR) based VAD is used in the period when the noise power is stationary, and the spectral entropy based VAD is implemented in the hang-over frames after the burst of noisy spectrum. Then a flag is set to control the update of noise estimation. Finally, an attenuated version of the noisy spectrum will be used directly as noise estimation if the update flag is set to one. The performance of the proposed method is evaluated under ITU-T G.160. In comparison with the conventional method, the convergence time is reduced evidently, while the abilities of noise reduction and SNR improvement are preserved, and the impact on the objective speech quality is constrained to a low level.
In this paper, we investigate the effects that the lossy image compression has on the performance competitive codes of palmprint verification algorithms. Effects of lossy compression on palmprint recognition performan...
详细信息
A novel characteristic waveform (CW) decomposition method based on bi-orthogonal lifting wavelet transform (BLWT) is proposed for CWI speech codec in this paper. Firstly, the complicated CW alignment operations are no...
详细信息
A novel characteristic waveform (CW) decomposition method based on bi-orthogonal lifting wavelet transform (BLWT) is proposed for CWI speech codec in this paper. Firstly, the complicated CW alignment operations are not necessary by using this method, and as a result the computational complexity can be greatly reduced. Secondly, the additional delay of CW decomposition based on traditional wavelet transform is cancelled by using boundary treatment. Thirdly, by omitting filter operations and adopting the situ calculation technique, the memory consumption of the proposed algorithm will be much smaller than the traditional one. In addition, the multi-resolution analysis capability of wavelet transform is preserved, which will make the parameter quantization more flexible and the scalab.e coding much easier to be realized. The performance evaluation shows that the proposed decomposition algorithm could fulfill the requirements of high quality, multi-rate speech compression, and is suitable for the real-time communication systems. The results of MOS and A/B listening test show that the performance of 1.84kb/s CWI coder based on this CW decomposition is very close to that of 2.4kbit/s MELP coder.
Seed sampling is critical in semi-supervised learning. This paper proposes a clustering-based stratified seed sampling approach to semi-supervised learning. First, various clustering algorithms are explored to partiti...
详细信息
Although many methods of refining initialization have appeared, the sensitivity of K-Means to initial centers is still an obstacle in applications. In this paper, we investigate a new class of clustering algorithm, K-...
详细信息
In this paper, the use of Independent Component Discriminant Analysis (ICDA) for remote sensing classification is proposed. ICDA is a non-parametric method for discriminant analysis based on the application of a Bayes...
详细信息
This paper presents a novel local-feature-based algorithm to track objects through frames. Real-time performance and occlusion are great challenges in object tracking. Local features are more distinctive than global f...
详细信息
This paper deals with a novel method for object tracking. In the first step interest points are detected and feature descriptors around them are calculated. Sets of known points are created, allowing tracking based on...
详细信息
Mobile phones and devices are evolving steadily, adding increasingly advanced capabilities. Today's smart phones, for example, have PClike functionality with complete operating system software that provides a plat...
详细信息
暂无评论