All-prosodic synthesis architecture

A. Dirksen; J.S. Coleman

All-prosodic synthesis architecture

A. Dirksen, J.S. Coleman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We present a speech synthesis architecture, IPOX, which allows the integration of various aspects of prosodic structure at different structural levels. This is achieved by using a hierarchical, metrical representation of the input string in analysis as well as phonetic interpretation. The output of the latter step consists of parameters for the Klatt synthesizer. The architecture is based primarily on YorkTalk (Coleman 1992, 1994; Local 1992), but differs in that it uses a rule compiler (Dirksen 1993), which allows a clean separation of linguistic statements and computational execution, as well as a more concise statement of various kinds of generalizations.

Original language	English
Title of host publication	Proceedings of the Second ESCA/IEEE Workshop on Speech Synthesis, New Paltz, NY, USA, September 12-15, 1994
Pages	232-235
Publication status	Published - 1994

Cite this

@inproceedings{92b0de308c614e728627d84b26315eb4,

title = "All-prosodic synthesis architecture",

abstract = "We present a speech synthesis architecture, IPOX, which allows the integration of various aspects of prosodic structure at different structural levels. This is achieved by using a hierarchical, metrical representation of the input string in analysis as well as phonetic interpretation. The output of the latter step consists of parameters for the Klatt synthesizer. The architecture is based primarily on YorkTalk (Coleman 1992, 1994; Local 1992), but differs in that it uses a rule compiler (Dirksen 1993), which allows a clean separation of linguistic statements and computational execution, as well as a more concise statement of various kinds of generalizations.",

author = "A. Dirksen and J.S. Coleman",

year = "1994",

language = "English",

pages = "232--235",

booktitle = "Proceedings of the Second ESCA/IEEE Workshop on Speech Synthesis, New Paltz, NY, USA, September 12-15, 1994",

}

TY - GEN

T1 - All-prosodic synthesis architecture

AU - Dirksen, A.

AU - Coleman, J.S.

PY - 1994

Y1 - 1994

N2 - We present a speech synthesis architecture, IPOX, which allows the integration of various aspects of prosodic structure at different structural levels. This is achieved by using a hierarchical, metrical representation of the input string in analysis as well as phonetic interpretation. The output of the latter step consists of parameters for the Klatt synthesizer. The architecture is based primarily on YorkTalk (Coleman 1992, 1994; Local 1992), but differs in that it uses a rule compiler (Dirksen 1993), which allows a clean separation of linguistic statements and computational execution, as well as a more concise statement of various kinds of generalizations.

AB - We present a speech synthesis architecture, IPOX, which allows the integration of various aspects of prosodic structure at different structural levels. This is achieved by using a hierarchical, metrical representation of the input string in analysis as well as phonetic interpretation. The output of the latter step consists of parameters for the Klatt synthesizer. The architecture is based primarily on YorkTalk (Coleman 1992, 1994; Local 1992), but differs in that it uses a rule compiler (Dirksen 1993), which allows a clean separation of linguistic statements and computational execution, as well as a more concise statement of various kinds of generalizations.

M3 - Conference contribution

SP - 232

EP - 235

BT - Proceedings of the Second ESCA/IEEE Workshop on Speech Synthesis, New Paltz, NY, USA, September 12-15, 1994

ER -

All-prosodic synthesis architecture

Abstract

Fingerprint

Cite this