Fine-grained sentiment analysis of Chinese microblog is investigated and a method of multi-strategy fusion is proposed. Firstly, the authors apply naive Bayesian to identify sentiment or non-sentiment about microblog. Secondly, based on emotion ontology, a method for how to form 21 sentiment features vectors of microblog is presented. At last, fine-grained sentiment of microblog is classified based on SVM and KNN respectively. Experiment results show that multi-strategy fusion is better than a single method, in addition, “NB+SVM” strategy is better than “NB+KNN” strategy.

The mergence of VoIP and WLAN created a new wireless platform for voice service delivery, VoWLAN. This paper figured out the capacity bottleneck of VoWLAN, and analyzed the problems in current solutions such as M-M. A novel unicast based multiplexing scheme (U-M, Unicast Multiplexing) to improve the capacity and performance of VoWLAN was proposed. Both theoretical and simulation results showed that this scheme improved the voice capacity to nearly 100% comparing to the traditional un-multiplexed scheme, and reduced the packet lost ratio by 10% compared with the M-M scheme. Meanwhile, the U-M scheme is a power-saving scheme in the voice-oriented application as well. Therefore the proposed U-M scheme is an effective solution to increase the voice capacity of WLAN and improve the performance of VoIP service.

The analysis of the relative importance of components of MFCC for both speech recognition and speaker recognition using DTW recognizer in various noise environments are given. For English digit and under the Euclidean distance definition, the experiment results show cepstral components from C₂ to C₁₆contain the most useful speaker information, while C₀ and C₁ are usually harm to speaker recognition. Cepstral terms from C₁ to C₁₂ are found to contain the most useful speech information. In both tasks, the additive noise decreases the relative importance of low MFCC terms faster than that of the middle and high MFCC terms, and the decrement depends on the speech SNR. The channel distortion will deteriorate low terms more than the middle and high MFCC terms in both tasks, also.