Automatic Voice Query Service for Multi-Accented Mandarin Speech

Automatic Voice Query Service can extremely reduce the artificial cost, which could improve the response efficiency for users. The automatic speech recognition (ASR) is one of the important component in AVQS. However, many dialect areas in China make the AVQS have to response the multi-accented Mandarin users by single acoustic model in ASR. This problem severely limits the accuracy of ASR for multi-accented speech in the AVQS. In this paper, a new framework for AVQS is proposed to improve the accuracy of response. Firstly, the fusion feature including iVector and filterbank acoustic features is used to train the Transformer-CTC model. Secondly, the transformer-CTC model is used to construct the end-to-end ASR. Finally, key words matching algorithm for AVQS based on fuzzy mathematic theory is proposed to further improve the accuracy of response. The results show that the final accuracy in our proposed framework for AVQS arrives at 91.5%. The proposed framework for AVQS can satisfy the service requirement of different areas in mainland of China. This research has a great significance for exploring the application value of artificial intelligence in the real scene.

Application of Fuzzy Mathematics Model in Evaluating Order Priority

The method of make-to-order has gradually become the primary mode of production. It is an extremely important ability for enterprises to make production scheduling and response to the changes of customer demand agiely. Therefore, this paper mainly deals with how to evaluating order priority in the mode of make-to-order. For this question, an evaluation index system and a model of fuzzy mathematic system evaluation are established. Through empirical analysis, the model and evaluation system are found feasible and valid.

Comprehensive Evaluation of the Designing Scheme of AUV Platform Performance by AHP Method

This paper divides the platform performance into three different aspects: general characteristics, hull property and concealment performance, from which we fully study the various factor index involved, use the AHP to build an integrated-assessed mathematic model of hierarchy of good distinct and structure of high efficiency and calculate the weight assessment indicator of each hierarchy. This paper uses AHP to build the general objective function of the designing scheme of platform property. By the statistical analysis of the tip of various property indexes of mass hull property data, we choose the corresponding subordinating degree functions in the fuzzy mathematic field to determine the appropriate subjection function, calculate the relevant degree of membership, and finally conduct the integrated assessment of mathematic model of the design of AUV platform performance system. We use C# language in the developing environment of VS2010 to develop the fuzzy-comprehensive-assessment software system of the designing scheme of AUV platform, and, we also use the software to analysis the systematic reliability of this scheme by living example. Through this work, we could offer a scientific and rational theory of technology for the support of underwater unmanned vehicle research department.

Research on Uncertain Factors Analysis and Optimization Model for Collaborative Manufacturing Process

To solve the synchronization problem of collaborative manufacturing the uncertain factors of collaborative manufacturing progress are analyzed and fuzzy mathematic descriptions are defined. Considering deviation degree between the dynamic scheduling and the original scheduling, a multi-objective optimization model was developed. With the current production state as initial state, according to the new manufacturing constraints of collaborative production chain, a feasible solution is found to satisfy the constraint conditions. A simulation experiment is carried out and obtained an optimal scheduling scheme.

Condition Assessment of Regenerative Heater Based on Fuzzy Comprehensive Evaluation

In order to evaluate the performance of regenerative heater comprehensively and scientifically, the fuzzy comprehensive evaluation model of regenerative heater is proposed on the basis of fuzzy mathematic theory as well as the relevant background knowledge of the problem. In the fist-level fuzzy comprehensive evaluation model, the evaluation indicator system was established taking the influence of the turbine load into consideration. The definition of “excellence degree” was given to show the relative approach degree between the quantitative indicator and the excellent indicator. Membership functions of fuzzy evaluation set were constructed based on the excellence degree. Knowledge in terms of twenty experts’ experience and historical data was used to determine the indicator weight set. In the second-level indicator fuzzy comprehensive evaluation model, four composition operator models were selected to conduct the fist-level evaluation. The proposed model turns out to be feasible and effective by three typical load conditions.

The Impact Tendency Evaluation of Coal Mine and Rock Based on Fuzzy Clustering Method

Fuzzy clustering is a kind of language approximation method. It is a multivariate analysis method to classify samples based on the attribute diversity by using fuzzy mathematic method. From the diversity and complexity of impact tendency indicators of coal mine and rock, paper started with extreme value standardization and combined the classification indicators of impact tendency of coal mine and rock, then determined the fuzzy rating, membership function and weight set. Afterwards, paper established the fuzzy similar matrix by using cosine method, then transformed it into equivalent matrix, and did the fuzzy clustering analysis at last. The result shows that the method overcomes the irrationalities which made by existence of impact tendency, achieves a more accurate classification and evaluation, and provides a new method to the comprehensive evaluation of coal rock impact tendency.