Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure

H.C. Leeuwen, van; E. Lindert, te

doi:10.1109/ICASSP.1991.150455

Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure

H.C. Leeuwen, van
, E. Lindert, te

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

Samenvatting

Speech Maker is a framework designed to be the basis of an implementation of a text-to-speech system. The core of Speech Maker is a multilevel synchronized information structure through which all information transferred between linguistic modules passes. A user interface is available to inspect and manipulate this structure in an interactive session, and a rule formalism to manipulate the information structure algorithmically by means of rules. The three together constitute the framework of Speech Maker, which is described.

Originele taal-2	Engels
Titel	Proceedings IEEE International conference on acoustics, speech and signal processing (ICASSP) 91, Toronto, Canada, May 14-17, 1991
Uitgeverij	Institute of Electrical and Electronics Engineers
ISBN van geprinte versie	0-7803-0003-3
DOI's	https://doi.org/10.1109/ICASSP.1991.150455
Status	Gepubliceerd - 1991

Toegang tot document

10.1109/ICASSP.1991.150455

Citeer dit

@inproceedings{6231dce739eb4cbe8843324185594213,

title = "Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure",

abstract = "Speech Maker is a framework designed to be the basis of an implementation of a text-to-speech system. The core of Speech Maker is a multilevel synchronized information structure through which all information transferred between linguistic modules passes. A user interface is available to inspect and manipulate this structure in an interactive session, and a rule formalism to manipulate the information structure algorithmically by means of rules. The three together constitute the framework of Speech Maker, which is described.",

author = "\{Leeuwen, van\}, H.C. and \{Lindert, te\}, E.",

year = "1991",

doi = "10.1109/ICASSP.1991.150455",

language = "English",

isbn = "0-7803-0003-3",

booktitle = "Proceedings IEEE International conference on acoustics, speech and signal processing (ICASSP) 91, Toronto, Canada, May 14-17, 1991",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure. / Leeuwen, van, H.C.; Lindert, te, E.
Proceedings IEEE International conference on acoustics, speech and signal processing (ICASSP) 91, Toronto, Canada, May 14-17, 1991. Institute of Electrical and Electronics Engineers, 1991.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

TY - GEN

T1 - Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure

AU - Leeuwen, van, H.C.

AU - Lindert, te, E.

PY - 1991

Y1 - 1991

N2 - Speech Maker is a framework designed to be the basis of an implementation of a text-to-speech system. The core of Speech Maker is a multilevel synchronized information structure through which all information transferred between linguistic modules passes. A user interface is available to inspect and manipulate this structure in an interactive session, and a rule formalism to manipulate the information structure algorithmically by means of rules. The three together constitute the framework of Speech Maker, which is described.

AB - Speech Maker is a framework designed to be the basis of an implementation of a text-to-speech system. The core of Speech Maker is a multilevel synchronized information structure through which all information transferred between linguistic modules passes. A user interface is available to inspect and manipulate this structure in an interactive session, and a rule formalism to manipulate the information structure algorithmically by means of rules. The three together constitute the framework of Speech Maker, which is described.

U2 - 10.1109/ICASSP.1991.150455

DO - 10.1109/ICASSP.1991.150455

M3 - Conference contribution

SN - 0-7803-0003-3

BT - Proceedings IEEE International conference on acoustics, speech and signal processing (ICASSP) 91, Toronto, Canada, May 14-17, 1991

PB - Institute of Electrical and Electronics Engineers

ER -

Speech maker: Text-to-speech synthesis based on a multi-level, synchronized data structure

Samenvatting

Toegang tot document

Vingerafdruk

Citeer dit