HMM-Based Speech Synthesis
Journal Title: International Journal of Modern Engineering Research (IJMER) - Year 2013, Vol 3, Issue 4
Abstract
This paper describes a approach to text-to-speech synthesis (TTS) based on HMM. In the proposing approach,speech spectral parameter sequences are generated from HMMs directly based on maximum likelihood criterion. By considering relationship between static and dynamic features during parameter generation, smooth spectral sequences aregenerated according to the statistics of static and dynamic parameters modelled by HMMs, resulting in natural sounding speech. In this paper, first, the algorithm for parameter generation is derived, and then the basic structure of an HMM based TTS system is described. Results of subjective experiments show the effectiveness of dynamic feature.
Authors and Affiliations
Smita Chopde
Keywords
Related Articles
- EP ID EP151525
- DOI -
- Views 111
- Downloads 0
ortizontal Aggregation in SQL for Data Mining Analysis to Prepare Data Sets
: Preparing a data set for analysis is generally the most time consuming task in a data mining project, requiring many complex SQL queries, joining tables and aggregating columns. Existing SQL aggregations have lim...
Effect of Molybdenum Disulphide on Physical Properties of Neodymium-Iron-Boron Bonded Magnet
The present paper reports the effect of molybdenum disulfide (MoS2) on magnetic and mechanical properties of neodymium iron boron (NdFeB) bonded magnet. Powder metallurgy process has been used to prepare the te...
Properties of Glass Fibre Reinforced Geopolymer Concrete
This paper presents results of an experimental program to determine mechanical properties of Glass fibre reinforced Geopolymer Concrete which contains fly ash, alkaline liquids, fine & course aggregates & g...
Photovoltaic-Biomass Gasifier Hybrid Energy System for a Poultry House
Availability and sustainability of energy and food production are the biggest challenge facing the world. Find out how to integrate poultry and animal farms with renewable energy technologies will lead to a greater...
Artificial Intelligence based optimization of weld bead geometry in laser welding of Al-Mg alloy sheet
This paper reports on a modeling and optimization of laser welding of aluminum-magnesium alloy thickness of 1.7mm. Regression analysis is used for modeling and Genetic algorithm is used for optimize the process par...