Publication Details

Advances in very low bit-rate speech coding using recognition and synthesis techniques

BAUDOIN, G.; CAPMAN, F.; ČERNOCKÝ, J.; EL CHAMI, F.; CHARBIT, M.; CHOLLET, G.; PETROVSKA-DELACRETAZ, D. Advances in very low bit-rate speech coding using recognition and synthesis techniques. Lecture Notes in Computer Science, 2002, vol. 2002, no. 2448, p. 269-276. ISSN: 0302-9743.
Czech title
Zlepšení kodování řeči na velmi nízkých bitových rychlostech
Type
journal article
Language
English
Authors
Baudoin Genevieve
Capman Francois
Černocký Jan, prof. Dr. Ing. (DCGM)
El Chami Fadi
Charbit Maurice
Chollet Gerard, Dr.
Petrovska-Delacretaz Dijana, Dr.
URL
Keywords

speech coding, very low bit-rate, data-driven units, ALISP

Abstract

Many current systems for automatic speech processing rely on sub-word units defined using phonetic knowledge. Our paper presents an alternative to this approach -- determination of speech units using {ALISP} (Automatic Language Independent Speech Processing) techniques. Such units were experimentally tested in a very low bit rate phonetic vocoder, where mean bit rates of hundreds bps for unit encoding were achieved. Improvements of the proposed coder and some links to ``classical'' approaches of speech synthesis are discussed. Based on the results of comparison of an ALISP segmentation with a phonetic alignment, we comment on the potential use of automatically derived units in speech recognition, speaker verification and language identification.

Published
2002
Pages
269–276
Journal
Lecture Notes in Computer Science, vol. 2002, no. 2448, ISSN 0302-9743
Book
Proc. 5th International Conference Text, Speech and Dialogue, TSD2002
ISBN
3-540-44129-8
Publisher
Springer Verlag
BibTeX 
@article{BUT41073,
  author="Genevieve {Baudoin} and Francois {Capman} and Jan {Černocký} and Fadi {El Chami} and Maurice {Charbit} and Gerard {Chollet} and Dijana {Petrovska-Delacretaz}",
  title="Advances in very low bit-rate speech coding using recognition and synthesis techniques",
  journal="Lecture Notes in Computer Science",
  year="2002",
  volume="2002",
  number="2448",
  pages="269--276",
  issn="0302-9743",
  url="http://www.fit.vutbr.cz/~cernocky/publi/2002/tsd2002_sympa.pdf"
}
Back to top