In this letter, we propose that directional antennas, combined with power management, be incorporated to reduce intersystem interference in a shared band overlaid high altitude platform station (HAPS)-terrestrial code division multiple access (CDMA) system. To eliminate the HAPS to terrestrial interference, the HAPS is accessed only via directional antennas under the proposed scheme. By doing so, the uplink power to the HAPS can accordingly be increased, so that the terrestrial to HAPS interference is also effectively suppressed.

In mobile computing environments, a problem may exist between loss recovery mechanisms employed by the TCP (transmission control protocol) and RLP (radio link protocol). It is because that local retransmissions performed by the RLP could interfere with the TCP end-to-end error recovery when there are long and correlated packet losses due to bursty channel errors. That is, a spurious timeout would occur at the transport layer. In this paper, a new method is proposed to effectively suppress the occurrence of TCP spurious timeouts. In this new method a small number of ACKs (acknowledgements) is buffered at the base station prior to the emergence of every bad state period in the wireless channel, and these ACKs are henceforth released by the base station one at a time to reset the TCP sender's retransmission timer. Comprehensive comparisons between the proposed method and a baseline method are conducted through simulations to show that the improvement in throughput performance can be as large as 22%.

It is well known that deploying a proxy at the boundary of wireless networks and the Internet is able to improve the performance of transmission control protocol (TCP) over wireless links. Snoop protocol, acting like a transport layer proxy, performs local retransmissions for packets corrupted by wireless channel errors. In this letter, an improvement for the Snoop protocol is proposed to shorten the time spent on local recovery by sending extra copies in every local retransmission attempt. This enables TCP to quickly return to normal, effectively eliminating several of the problems that may cause throughput degradation.

Online learning is a method which updates the model gradually and can modify and strengthen the previous model, so that the updated model can adapt to the new data without having to relearn all the data. However, the accuracy of the current online multiclass learning algorithm still has room for improvement, and the ability to produce sparse models is often not strong. In this paper, we propose a new Multiclass Truncated Gradient Confidence-Weighted online learning algorithm (MTGCW), which combine the Truncated Gradient algorithm and the Confidence-weighted algorithm to achieve higher learning performance. The experimental results demonstrate that the accuracy of MTGCW algorithm is always better than the original CW algorithm and other baseline methods. Based on these results, we applied our algorithm for phishing website recognition and image classification, and unexpectedly obtained encouraging experimental results. Thus, we have reasons to believe that our classification algorithm is clever at handling unstructured data which can promote the cognitive ability of computers to a certain extent.

Dysarthric speech results from damage to the central nervous system involving the articulator, which can mainly be characterized by poor articulation due to irregular sub-glottal pressure, loudness bursts, phoneme elongation, and unexpected pauses during utterances. Since dysarthric speakers have physical disabilities due to the impairment of their nervous system, they cannot easily control electronic devices. For this reason, automatic speech recognition (ASR) can be a convenient interface for dysarthric speakers to control electronic devices. However, the performance of dysarthric ASR severely degrades when there is background noise. Thus, in this paper, we propose a noise reduction method that improves the performance of dysarthric ASR. The proposed method selectively applies either a Wiener filtering algorithm or a Kalman filtering algorithm according to the result of voiced or unvoiced classification. Then, the performance of the proposed method is compared to a conventional Wiener filtering method in terms of ASR accuracy.

In this paper, we propose a new mask estimation method for the computational auditory scene analysis (CASA) of speech using two microphones. The proposed method is based on a hidden Markov model (HMM) in order to incorporate an observation that the mask information should be correlated over contiguous analysis frames. In other words, HMM is used to estimate the mask information represented as the interaural time difference (ITD) and the interaural level difference (ILD) of two channel signals, and the estimated mask information is finally employed in the separation of desired speech from noisy speech. To show the effectiveness of the proposed mask estimation, we then compare the performance of the proposed method with that of a Gaussian kernel-based estimation method in terms of the performance of speech recognition. As a result, the proposed HMM-based mask estimation method provided an average word error rate reduction of 61.4% when compared with the Gaussian kernel-based mask estimation method.

This paper proposes a deep neural network (DNN) based framework to address the problem of vector quantization (VQ) for high-dimensional data. The main challenge of applying DNN to VQ is how to reduce the binary coding error of the auto-encoder when the distribution of the coding units is far from binary. To address this problem, three fine-tuning methods have been adopted: 1) adding Gaussian noise to the input of the coding layer, 2) forcing the output of the coding layer to be binary, 3) adding a non-binary penalty term to the loss function. These fine-tuning methods have been extensively evaluated on quantizing speech magnitude spectra. The results demonstrated that each of the methods is useful for improving the coding performance. When implemented for quantizing 968-dimensional speech spectra using only 18-bit, the DNN-based VQ framework achieved an averaged PESQ of about 2.09, which is far beyond the capability of conventional VQ methods.