Research on predicting prosodic parameters for Chinese synthesis by data mining approach

Prosodic control is an important part of speech synthesis system. Prosodic parameters choice right or wrong influences the quality of synthetic speech directly. At present, text to speech system has less effective describe to reflect data relationships in the corpus. A new research approach - data mining technology to discover those relationships by association rules modeling is presented. And a new algorithm for generating association rules of prosodic parameters including pitch parameters and duration parameters from corpus is developed. The output rules improve the correctness of syllable choice in text to speech system.

Parametric sensitivity analysis of precipitation and temperature based on multi-uncertainty quantification methods in the Weather Research and Forecasting model

Sensitivity analysis(SA) has been widely used to screen out a small number of sensitive parameters for model outputs from all adjustable parameters in weather and climate models, helping to improve model predictions by tuning the parameters. However, most parametric SA studies have focused on a single SA method and a single model output evaluation function, which makes the screened sensitive parameters less comprehensive. In addition, qualitative SA methods are often used because simulations using complex weather and climate models are time-consuming. Unlike previous SA studies, this research has systematically evaluated the sensitivity of parameters that affect precipitation and temperature simulations in the Weather Research and Forecasting(WRF) model using both qualitative and quantitative global SA methods. In the SA studies, multiple model output evaluation functions were used to conduct various SA experiments for precipitation and temperature. The results showed that five parameters(P3, P5, P7, P10, and P16) had the greatest effect on precipitation simulation results and that two parameters(P7 and P10) had the greatest effect for temperature. Using quantitative SA, the two-way interactive effect between P7 and P10 was also found to be important, especially for precipitation. The microphysics scheme had more sensitive parameters for precipitation, and P10(the multiplier for saturated soil water content) was the most sensitive parameter for both precipitation and temperature. From the ensemble simulations, preliminary results indicated that the precipitation and temperature simulation accuracies could be improved by tuning the respective sensitive parameter values, especially for simulations of moderate and heavy rain.

Distributed emitter parameter refinement based on maximum likelihood

Purpose-Emitter parameter estimation via signal sorting is crucial for communication,electronic reconnaissance and radar intelligence analysis.However,due to problems of transmitter circuit,environmental noises and certain unknown interference sources,the estimated emitter parameter measurements are still inaccurate and biased.As a result,it is indispensable to further refine the parameter values.Though the benchmark clustering algorithms are assumed to be capable of inferring the true parameter values by discovering cluster centers,the high computational and communication cost makes them difficult to adapt for distributed learning on massive measurement data.The paper aims to discuss these issues.Design/methodology/approach-In this work,the author brings forward a distributed emitter parameter refinement method based on maximum likelihood.The author’s method is able to infer the underlying true parameter values from the huge measurement data efficiently in a distributed working mode.Findings-Experimental results on a series of synthetic data indicate the effectiveness and efficiency of the author’s method when compared against the benchmark clustering methods.Originality/value-With the refined parameter values,the complex stochastic parameter patterns could be discovered and the emitters could be identified by merging observations of consistent parameter values together.Actually,the author is in the process of applying her distributed parameter refinement method for PRI parameter pattern discovery and emitter identification.The superior performance ensures its wide application in both civil and military fields.