What can basic research contribute to speech synthesis?  

Oleh:

Fant, G.

Jenis: Article from Journal - ilmiah internasional
Dalam koleksi: Journal of Phonetics vol. 19 no. 1 (Jan. 1991), page 75 - 90.

Ketersediaan

Perpustakaan PKBB Nomor Panggil: 405/JOP/19 Non-tandon: tidak ada Tandon: 1

Lihat Detail Induk

Isi artikel

What can be done to improve the performance of text-to-speech systems, to meet the demands for increase of intelligibility, naturalness, and flexibility in adopting to various speaker and voice characteristics, speaking style, message types, etc.? The basic problems lie less in our synthesis peripherals than in a knowledge gap concerning the speech code, but we are also limited by the constraints of present rule systems. Examples of minimally contrasting stop consonant features and some typical confusions are discussed. Segmental and prosodic features are more intimately connected than is usually recognized. Interaction effects are discussed. Special attention is devoted to voice source features and to stress correlates and the temporal organization of interstress intervals and pauses. The further development of synthesis should be guided by articulatory modelling of control functions, eventually leading to complete articulatory synthesis.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali