Prosodic Models in Speech Technology

Entrance requirements

M.Sc. LST: Speech Science

Course description

Course credits

Active participation on a regular basis required.

Structure

Literature

BibTex entries of all references (books, papers, URL):

@InCollection{Batliner/Mobius:2005,
  author = 	 {Batliner, Anton and M{\"o}bius, Bernd},
  title = 	 {Prosodic models, automatic speech understanding, and
		  speech synthesis: Towards the common ground?},
  booktitle = 	 {The Integration of Phonetic Knowledge in Speech Technology},
  publisher =	 {Springer},
  year =	 2005,
  editor =	 {Barry, William~J. and van Dommelen, Wim~A.},
  address =	 {Dordrecht},
  pages =	 {21--44}
}

@InCollection{Batliner/etal:2000c,
  author = 	 {Batliner, Anton and Buckow, J. and Niemann, Heinrich
		  and N{\"o}th, Elmar and Warnke, Volker},
  title = 	 {The prosody module},
  booktitle =    {Verbmobil: Foundations of Speech-to-Speech Translation},
  publisher =    {Springer},
  year =         2000,
  editor =       {Wahlster, Wolfgang},
  address =      {Berlin},
  pages = 	 {106--121}
}

@Article{Botinis/etal:2001,
  author =       {Botinis, Antonis and Granstr{\"o}m, Bj{\"o}rn and
                  M{\"o}bius, Bernd},
  title =        {Developments and paradigms in intonation research},
  journal =      {Speech Communication},
  year =         2001,
  volume =       33,
  number =       4,
  pages =        {263--296}
}

@InCollection{Fujisaki:1988,
  author = 	 {Fujisaki, Hiroya},
  title = 	 {A note on the physiological and physical basis for the
		  phrase and accent components in the voice fundamental
		  frequency contour},
  booktitle = 	 {Vocal Physiology: Voice Production, Mechanisms and
		  Functions},
  publisher =	 {Raven},
  year =	 1988,
  editor =	 {Fujimura, Osamu},
  address =	 {New York},
  pages =	 {347--355}
}

@Article{Jilka/etal:1999,
  author =       {Jilka, Matthias and M{\"o}hler, Gregor and Dogil,
                  Grzegorz},
  title =        {{Rules for the generation of ToBI-based American
                  English intonation}},
  journal =      {Speech Communication},
  year =         1999,
  volume =       28,
  pages =        {83--108}
}

@InProceedings{Mobius:1995,
  author = 	 {M{\"o}bius, Bernd},
  title = 	 {Components of a quantitative model of {G}erman
		  intonation},
  booktitle =    {Proceedings of the 13th International Congress of
                  Phonetic Sciences (Stockholm)},
  year =         1995,
  volume =       2,
  pages =	 {108--115}
}

@Article{Pierrehumbert:1981,
  author = 	 {Pierrehumbert, Janet},
  title = 	 {Synthesizing intonation},
  journal = 	 {Journal of the Acoustical Society of America},
  year = 	 1981,
  volume =	 70,
  pages =	 {985--995}
}

@InCollection{Santen/Mobius:2000,
  author = 	 {van Santen, Jan P.~H. and M{\"o}bius, Bernd},
  title = 	 {A quantitative model of {F0} generation and alignment},
  editor = 	 {Botinis, Antonis},
  booktitle = 	 {Intonation---Analysis, Modelling and Technology},
  publisher = 	 {Kluwer},
  year = 	 2000,
  address =      {Dordrecht},
  pages =        {269--288}
}

@@Article{Santen/Shih:2000,
  author =       {van Santen, Jan P.~H. and Shih, Chilin},
  title =        {Suprasegmental and segmental timing models in
                  {M}andarin {C}hinese and {A}merican {E}nglish},
  journal =      {Journal of the Acoustical Society of America},
  year =         2000,
  volume =       107,
  number =       2,
  pages =        {1012--1026}
}

Article{Santen:1994,
  author = 	 {van Santen, Jan P.~H.},
  title = 	 {Assignment of segmental duration in text-to-speech
		  synthesis},
  journal = 	 {Computer Speech and Language},
  year = 	 1994,
  volume =	 8,
  pages =	 {95--128}
}

@InCollection{Santen:1998,
  author =       {van Santen, Jan P. H.},
  title =        {Timing},
  booktitle = 	 {Multilingual Text-to-Speech Synthesis: The {B}ell
                  {L}abs Approach},
  editor =       {Sproat, Richard},
  publisher = 	 {Kluwer},
  year = 	 1998,
  address =	 {Dordrecht},
  pages =        {115--139}
}

@InCollection{Shriberg/Stolcke:2004,
  author = 	 {Shrberg, Elizabeth and Stolcke, Andreas},
  title = 	 {Prosody modeling for automatic speech recognition
                  and understanding},
  booktitle = 	 {Mathematical Foundations of Speech and Language Processing},
  pages = 	 {105--114},
  publisher = {Springer},
  year = 	 2004,
  editor = 	 {Johnson, Mark and Khudanpur, S. and Ostendorf, Mari
                  and Rosenfeld, R.},
  volume = 	 138,
  series = 	 {IMA Volumes in Mathematics and Its Applications}
}

@Article{Shriberg/etal:2000,
  author =       {Shriberg, Elizabeth and Stolcke, Andreas and
                  Hakkani-T{\"u}r, Dilek and T{\"u}r, G{\"o}khan},
  title =        {Prosody-based automatic segmentation of speech into
                  sentences and topics},
  journal =      {Speech Communication},
  year =         2000,
  volume =       32,
  number =       {1--2},
  pages =        {??}
}

@InCollection{Zeissler/etal:2006a,
  author = 	 {Zei{\ss}ler, Viktor and Adelhardt, Johann and
                  Batliner, Anton and Frank, Carmen and N{\"o}th,
                  Elmar and Shi, Rui Ping and Niemann, Heinrich},
  title = 	 {The prosody module},
  booktitle = 	 {{SmartKom}: Foundations of Multimodal Dialogue Systems},
  editor =	 {Wahlster, Wolfgang},
  publisher = 	 {Springer},
  year = 	 2006,
  pages =	 {139--152}
}