Speech Synthesis by Rule: An Acoustic Domain Approach

Abstract

A novel approach to speech synthesis by rule is presented and evaluated. A discrete set of input symbols is converted to continuous control signals for driving a serial terminal analog speech synthesizer. The synthesizer converts the control signals to a continuous acoustic output. The synthesizer was simulated on a digital computer. The input set is a linguistic description of the utterance. It includes information about which phonemes are present, which vowels are stressed, and where sentence and word boundaries and pauses occur.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1967
Accession Number
ADA459694

Entities

People

  • Lawrence R. Rabiner

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Availability
  • Boundaries
  • Classification
  • Computers
  • Contracts
  • Digital Computers
  • Information Operations
  • Instructions
  • Massachusetts
  • Monitoring
  • Security
  • Standards
  • Terminals

Readers

  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation