FarsBayan: A Unit Selection based
نویسندگان
چکیده
In recent years, the unit selection-based concatenative speech synthesis method using a large corpus has attracted great attention. This method provides more natural quality speech compared to the parameter driven methods. The Formant Synthesis, HNM method and use of MLSA filter are the prevalent methods for synthesizing Farsi speech. In this paper, we present the structure of a proposed unit selection synthesizer for Farsi language. In the proposed system, the linear regression method has been used for determination of weights of discrete sub-costs in the target cost, while the weights of other sub-costs have been considered constant. We have also presented a preselection algorithm using adaptive threshold for pruning the units. In addition, the efficiency of TD-PSOLA algorithm in improvement of resulting speech quality has been studied. Informal tests show the degrading effect of this algorithm on the output quality. The output speech was found to be remarkably fluent and natural. The quality of the output speech has been evaluated using MOS subjective test, and we have obtained a MOS test value of 3.8 for overall quality.
منابع مشابه
Study on Unit-Selection and Statistical Parametric Speech Synthesis Techniques
One of the interesting topics on multimedia domain is concerned with empowering computer in order to speech production. Speech synthesis is granting human abilities to the computer for speech production. Data-based approach and process-based approach are the two main approaches on speech synthesis. Each approach has its varied challenges. Unit-selection speech synthesis and statistical parametr...
متن کاملAn Intelligence-Based Model for Supplier Selection Integrating Data Envelopment Analysis and Support Vector Machine
The importance of supplier selection is nowadays highlighted more than ever as companies have realized that efficient supplier selection can significantly improve the performance of their supply chain. In this paper, an integrated model that applies Data Envelopment Analysis (DEA) and Support Vector Machine (SVM) is developed to select efficient suppliers based on their predicted efficiency sco...
متن کاملSelection of Cow Cockle (Vaccaria hispanica) Ecotypes based on Agronomic Traits under Different Irrigation Regimes
Extended Abstract Introduction and Objective: The cow cockle has a great potential for producing medicinal products due to its triterpenoid saponins. This experiment was aimed to investigate different cow cockle ecotypes under drought stress conditions and select the tolerant ecotype(s) based on agronomic traits using selection indices under different irrigation regimes. Materials and Methods...
متن کاملA Fuzzy Based Mathematical Model for Vendor Selection and Procurement Planning with Multiple Discounts in the Presence of Supply Uncertainty
Supplier selection and material procurement planning are the most important issues in supply chain management. This decision is complicated when the buyers face with discount price schemes. In real situation, each supplier may apply different methods such as different types of discount schedules and various types of payment in order to increase market share. In this situation, buyers try to sel...
متن کاملThe impact of household characters on choosing a house: the housing unit and quality of access to urban facilities Case study: Tehran City
Introduction: The "life cycle" theory is the most important tool for understanding the relationship among characteristics of housing and households, which reflects the behavior of households in the city. The theory, households are defined based on characteristics such as household size, number of students, employment status, income, age of household, etc. Every household, based on what are thei...
متن کامل