Modeling segmental duration with multivariate adaptive regression splines
نویسنده
چکیده
The application of “Multivariate Adaptive Regression Splines”(MARS) to the problem of modeling duration of a set of segments used in a text-to-speech system for German is presented. MARS is a technique to estimate general functions of high-dimensional arguments given sparse data. It automatically selects the parameters and the structure of the model based on data available. The result is a model with a correlation coefficient between observed and predicted durations of a test set of . Besides highly accurate predicting durations, a MARS model also allows interpretation of its structure, demonstrated in this study by analyses of factor importance and interactions of the MARS model.
منابع مشابه
GENETIC PROGRAMMING AND MULTIVARIATE ADAPTIVE REGRESION SPLINES FOR PRIDICTION OF BRIDGE RISKS AND COMPARISION OF PERFORMANCES
In this paper, two different data driven models, genetic programming (GP) and multivariate adoptive regression splines (MARS), have been adopted to create the models for prediction of bridge risk score. Input parameters of bridge risks consists of safe risk rating (SRR), functional risk rating (FRR), sustainability risk rating (SUR), environmental risk rating (ERR) and target output. The total ...
متن کاملESTIMATING DRYING SHRINKAGE OF CONCRETE USING A MULTIVARIATE ADAPTIVE REGRESSION SPLINES APPROACH
In the present study, the multivariate adaptive regression splines (MARS) technique is employed to estimate the drying shrinkage of concrete. To this purpose, a very big database (RILEM Data Bank) from different experimental studies is used. Several effective parameters such as the age of onset of shrinkage measurement, age at start of drying, the ratio of the volume of the sample on its drying...
متن کاملWeighted neural network ensemble models for speech prosody control
In text-to-speech synthesis systems, the quality of the predicted prosody contours influences quality and naturalness of synthetic speech. This paper presents a new statistical model for prosody control that combines an ensemble learning technique using neural networks as base learners with feature relevance determination. This weighted neural network ensemble model was applied for both, phone ...
متن کاملA two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines
The objective of the proposed study is to explore the performance of credit scoring using a two-stage hybrid modeling procedure with artificial neural networks and multivariate adaptive regression splines (MARS). The rationale under the analyses is firstly to use MARS in building the credit scoring model, the obtained significant variables are then served as the input nodes of the neural networ...
متن کامل