Simulation of Human Speech Production Applied to the Study and Synthesis of European Portuguese
- PDF / 1,219,596 Bytes
- 14 Pages / 612 x 792 pts (letter) Page_size
- 14 Downloads / 145 Views
Simulation of Human Speech Production Applied to the Study and Synthesis of European Portuguese ´ Antonio J. S. Teixeira Instituto de Engenharia Electr´onica e Telem´atica de Aveiro (IEETA), 3810-193 Aveiro, Portugal Departamento de Electr´onica e Telecomunicac¸o˜es, Universidade de Aveiro, 3810-193 Aveiro, Portugal Email: [email protected]
Roberto Martinez Instituto de Engenharia Electr´onica e Telem´atica de Aveiro (IEETA), 3810-193 Aveiro, Portugal Email: [email protected]
Lu´ıs Nuno Silva Instituto de Engenharia Electr´onica e Telem´atica de Aveiro (IEETA), 3810-193 Aveiro, Portugal Email: [email protected]
Luis M. T. Jesus Instituto de Engenharia Electr´onica e Telem´atica de Aveiro (IEETA), 3810-193 Aveiro, Portugal Escola Superior de Sa´ude, Universidade de Aveiro, 3810-193 Aveiro, Portugal Email: [email protected]
Jose C. Pr´ıncipe Computational Neuroengineering Laboratory (CNEL), University of Florida, Gainesville, FL 32611, USA Email: [email protected]
Francisco A. C. Vaz Instituto de Engenharia Electr´onica e Telem´atica de Aveiro (IEETA), 3810-193 Aveiro, Portugal Departamento de Electr´onica e Telecomunicac¸o˜es, Universidade de Aveiro, 3810-193 Aveiro, Portugal Email: [email protected] Received 29 October 2003; Revised 31 August 2004 A new articulatory synthesizer (SAPWindows), with a modular and flexible design, is described. A comprehensive acoustic model and a new interactive glottal source were implemented. Perceptual tests and simulations made possible by the synthesizer contributed to deepening our knowledge of one of the most important characteristics of European Portuguese, the nasal vowels. First attempts at incorporating models of frication into the articulatory synthesizer are presented, demonstrating the potential of performing fricative synthesis based on broad articulatory configurations. Synthesis of nonsense words and Portuguese words with vowels and nasal consonants is also shown. Despite not being capable of competing with mainstream concatenative speech synthesis, the anthropomorphic approach to speech synthesis, known as articulatory synthesis, proved to be a valuable tool for phonetics research and teaching. This was particularly true for the European Portuguese nasal vowels. Keywords and phrases: articulatory synthesis, speech production, European Portuguese, nasal vowels, fricatives.
1.
INTRODUCTION
Recent technological developments are characterized by increasing physical and psychological similarity to humans. One example is the well-known human-like robots. Being one of the distinct characteristics of humans, speech is a
natural candidate to imitation by machines. Also, information can be transmitted very fast and speech frees hands and eyes for other tasks. Various designs of machines that produce and understand human speech have been available for a long time [1, 2]. The use of voice in computer systems interfaces will
1436 be an added advantage, allowing, for example, the use of information systems for people with different disabilities and the access by telephone to n
Data Loading...
