BibTeX entries in bib/speech-s.bib
@BOOK{speechsyn96,
editor = {J.P.H. van Santen and J. Hirschberg and J. Olive and R. Sproat},
title = {{Progress in Speech Synthesis}},
publisher = {Springer-Verlag},
address = {New York},
year = {1996},
isbn = {0-387-94701-9},
amazon-url = {http://www.amazon.de/exec/obidos/ASIN/0387947019},
remarks = {van Santen Author Links: \url{http://www.bell-labs.com/project/tts/BOOK.html}, Springer Heidelberg: \url{http://www.springer.de/cgi-bin/search_book.pl?isbn=0-387-94701-9}, Springer New-York: \url{http://www.springer-ny.com/catalog/np/may96np/DATA/0-387-94701-9.html}},
}
@ARTICLE{psola92,
key = {synthesis},
author = {H. Valbret and E. Moulines and J. P. Tubach},
title = {Voice transformation using {PSOLA} technique},
journal = {speech},
year = {1992},
month = {June},
volume = {11},
number = {2-3},
pages = {189--194},
}
@BOOK{chomsky68sound,
author = {N. Chomsky and M. Halle},
title = {The Sound Pattern of English},
publisher = {Harper \& Row},
address = {New York, NY},
year = {1968},
}
@ARTICLE{bailly1991,
author = {G. Bailly and R. Laboissi\`{e}re and J. L. Schwartz},
title = {Formant trajectories as audible gestures: an alternative for speech synthesis.},
journal = {Journal of Phonetics},
year = {1991},
volume = {19},
pages = {9--23},
}
@INPROCEEDINGS{soong88,
author = {F.K. Soong and A.E. Rosenberg},
title = {On the use of Instantaneous and Transitional Spectral Information in Speaker Recognition},
booktitle = {IEEE Transactions on Acoustics, Speech and Signal Processing},
volume = {36},
year = {1988},
pages = {871--879},
note = {},
keywords = {derivative of cepstrum},
remarks = {cited in \cite{tcts:iscas97}},
abstract = {},
}
@INPROCEEDINGS{griffin88,
author = {D.W. Griffin and J.S. Lim},
title = {Multiband Excitation Vocoder},
booktitle = {IEEE Transactions on Acoustics, Speech and Signal Processing},
volume = {36},
year = {1988},
pages = {1123--1235},
note = {},
keywords = {robust cepstrum by sinusoidal weighting},
remarks = {cited in \cite{tcts:iscas97}},
abstract = {},
}
@INPROCEEDINGS{allessandro95,
author = {C. d'Alessandro and P. Mertens},
title = {Automatic pitch contour stylization using a model of tonal perception},
booktitle = {Computer Speech and Language},
year = {1995},
pages = {257--288},
note = {},
keywords = {perceptual stylization, based on a model of tonal perception},
remarks = {cited in \cite{tcts:iscas97}},
abstract = {},
}
@INPROCEEDINGS{traber92,
author = {C. Traber},
title = {{F0 Generation with a Database of Natural F0 Patterns and with a Neural Network}},
booktitle = {Talking Machines: Theories, Models, and Designs},
editor = {G. Bailly and C. Benot},
publisher = {North Holland},
year = {1992},
pages = {287--304},
note = {},
remarks = {cited in \cite{tcts:iscas97}: machine learning techniques: multilayer perceptrons},
abstract = {},
}
@INPROCEEDINGS{sagisaka92,
author = {Y. Sagisaka and N. Kaiki},
title = {{Optimization of Intonation Control Using Statistical F0 Resetting Characteristics}},
booktitle = {Proceedings of the International Conference on Acoustics},
volume = {2},
publisher = {Speech and Signal Processing},
year = {1992},
pages = {49--52},
note = {},
remarks = {cited in \cite{tcts:iscas97}: machine learning techniques: linear regression},
abstract = {},
}
@INPROCEEDINGS{hirschberg91,
author = {J. Hirschberg},
title = {{Using Text Analysis to Predict Intonational Boundaries}},
booktitle = {Proceedings of Eurospeech},
location = {Genova},
year = {1991},
pages = {1275--1278},
note = {},
remarks = {},
abstract = {},
}
@INPROCEEDINGS{moebius93,
author = {B. M{\"o}bius and M. P{\"a}tzold and W. Hess},
title = {{Analysis and Synthesis of German F0 Contours by Means of Fujisaki's Model}},
booktitle = {Speech Communication},
volume = {13},
year = {1993},
pages = {53--61},
note = {},
remarks = {},
abstract = {},
}
@INPROCEEDINGS{sagisaka88,
author = {Y. Sagisaka},
title = {{Speech synthesis by rule using an optimal selection of non-uniform synthesis units}},
booktitle = {Proc. of the Int'l Conf. on Acoustics, Speech, and Signal Processing},
publisher = {},
year = {1988},
pages = {679},
note = {},
remarks = {(origin of unit selection?), cited in \cite{cslu:esca98mm}: since the late 1980's, selection-based concatenative synthesis from large databases has received increased interest as a potential improvement upon fixed diphone inventories. \tbf},
abstract = {},
}
@INPROCEEDINGS{wang93,
author = {W. J. Wang and W. N. Campbell and N. Iwahashi and Y. Sagisaka},
title = {{Tree-based unit selection for English speech synthesis}},
booktitle = {Proc. of the Int'l Conf. on Acoustics, Speech, and Signal Processing},
volume = {},
publisher = {},
year = {1993},
pages = {191--194},
note = {},
remarks = {cited in \cite{cslu:esca98mm, cslu:icslp98cronk}: clustering and decision trees. \tbf},
abstract = {},
}
@INPROCEEDINGS{nakajima94,
author = {S. Nakajima},
title = {{Automatic synthesis unit generation for English speech synthesis based on multi-layered context oriented clustering}},
booktitle = {Speech Communication},
volume = {14},
month = {September},
year = {1994},
pages = {313},
note = {},
remarks = {cited in \cite{cslu:esca98mm, cslu:icslp98cronk}: clustering and decision trees. \tbf},
abstract = {},
}
@PHDTHESIS{donovan96,
author = {R. E. Donovan},
title = {Trainable Speech Synthesis},
type = {PhD thesis},
school = {Cambridge University},
year = {1996},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: Mahalanobis distance},
abstract = {},
}
@INPROCEEDINGS{huang96,
author = {X. D. Huang and A. Acero and et al.},
title = {{Whistler: A trainable text-to-speech system}},
booktitle = {Proc. of the Int'l Conf. on Spoken Language Processing},
year = {1996},
pages = {2387--2390},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: decision trees for speech synthesis},
abstract = {},
}
@INPROCEEDINGS{karaali96,
author = {O. Karaali and G. Corrigan and I. Gerson},
title = {{Speech Synthesis with Neural Networks}},
booktitle = {Proc. of World Congress on Neural Networks},
month = {September},
year = {1996},
pages = {45--50},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: data driven direct mapping with NN},
abstract = {},
}
@INPROCEEDINGS{tuerk93,
author = {C. Tuerk and T. Robinson},
title = {{Speech synthesis using artificial neural networks trained on cepstral coefficients}},
booktitle = {Proc. EUROSPEECH},
pages = {1713--1716},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: data driven direct mapping with NN},
abstract = {},
}
@BOOK{quackenbush88,
author = {S. R. Quackenbush and T. P. Barnwell and M. A. Clements},
title = {{Objective Measures of Speech Quality}},
publisher = {Prentice-Hall},
address = {Englewood Cliffs, NJ},
year = {1988},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: distance measures for coding},
abstract = {},
}
@INPROCEEDINGS{nocerino85,
author = {N. Nocerino and F. K. Soong and L. R. Rabiner and D. H Klatt},
title = {{Comparative study of several distortion measures for speech recognition}},
booktitle = {Speech Communication},
volume = {4},
year = {1985},
pages = {317--331},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: distance measures for ASR},
abstract = {},
}
@INPROCEEDINGS{asp:icassp88,
author = {H. Hermansky and J. C. Junqua},
title = {{Optimization of perceptually-based ASR front-end}},
booktitle = {Proceedings of the International Conference on Acoustics, Speech, and Signal Processing},
year = {1988},
pages = {219},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: distance measures for ASR},
abstract = {},
}
@INPROCEEDINGS{ghitza97,
author = {O. Ghitza and M. M. Sondhi},
title = {{On the perceptual distance between two speech segments}},
booktitle = {Journal of the Acoustical Society of America},
year = {1997},
volume = {101},
pages = {522--529},
number = {1},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: distance measures in general},
abstract = {},
}
@INPROCEEDINGS{hansen98,
author = {J. H. L. Hansen and D. T. Chappell},
title = {{An auditory-based distortion measure with application to concatenative speech synthesis}},
booktitle = {IEEE Trans. on Speech and Audio Processing},
volume = {6},
month = {September},
year = {1998},
pages = {489--495},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: distance measures for concatenative speech synthesis},
abstract = {},
}
@INPROCEEDINGS{asp:itsa94,
author = {H. Hermansky and N. Morgan},
title = {{RASTA processing of speech}},
booktitle = {IEEE Transactions on Speech and Acoustics},
volume = {2},
month = {October},
year = {1994},
pages = {587--589},
note = {},
remarks = {cited in \cite{cslu:esca98mm}},
abstract = {},
}
@BOOK{edwards93,
author = {A. L. Edwards},
title = {{An Introduction to Linear Regression and Correlation}},
publisher = {W. H. Freeman and Co},
address = {San Francisco},
year = {1993},
note = {},
remarks = {cited in \cite{cslu:esca98mm}: Fisher transform},
abstract = {},
}
@INPROCEEDINGS{Ding_OptiUnit_EURO97,
author = {Wen Ding and Nick Campbell},
title = {Optimising Unit Selection with Voice Source and Formants in the {CHATR} Speech Synthesis System},
booktitle = {Proc. Eurospeech '97},
address = {Rhodes, Greece},
month = {September},
year = {1997},
pages = {537--540},
remarks = {To BE FOUND!},
}
This document was translated from LATEX by
HEVEA.