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

Displacement in Load Bearing Straw Bale Walls Due To Concentric Compressive Loading

The objective of this research was to provide structural performance data and information for straw bale home builders, building inspectors and engineers. Structural testing of 2 full-scale straw bale walls was undertake...

A Novel Multi Copy Routing Scheme for Delay Tolerant Networks

A delay tolerant network (DTN) is a network designed to operate effectively over extreme distances such as those encountered in space communications or on an interplanetary scale. In such an environment, long latency --...

Finite Element Analysis of Convective Micro Polar Fluid Flow through a Porous Medium in Cylindrical Annulus

We analyze a finite element solution for the mixed convection micro polar flow through a porous medium in a cylindrical annulus. The governing partial differential equations are solved numerically by using finite element...

 Pulsation and Vibration Study Of Reciprocating Compressor According To API 618 5th Edition

 The compressor package contains the reciprocating compressor, pulsation dampers, gas coolers and the connected pipe system which are often the heart of an installation and should be operate smoothly and reliably. T...

On Characterizations of NANO RGB-Closed Sets in NANO Topological Spaces

The purpose of this paper is to establish and derive the theorems which exhibit the characterization of nano rgb-closed sets in nano topological space and obtain some of their interesting properties. We also us...

Download PDF file
  • EP ID EP151525
  • DOI -
  • Views 119
  • Downloads 0

How To Cite

Smita Chopde (2013).  HMM-Based Speech Synthesis. International Journal of Modern Engineering Research (IJMER), 3(4), 1894-1899. https://europub.co.uk/articles/-A-151525