MSc Language Science and Technology / LCT
Wed 16:15-17:45, C7.2/5.09
Reading: For each class, you are required to read one or two papers (see Schedule). For each paper, please send me one question that you want to be answered or discussed in class (on the day preceding the class, before midnight).
Presentation: An oral presentation of 30-45 minutes, typically based on a core paper and maybe some complementary reading. Please contact me (1) when you have been assigned a topic/paper and want to start working on it; (2) when you have a pre-final draft version of the presentation. After your presentation I will provide feedback to you. The final version of your slides will be posted on the course homepage.
Term Paper: MSc students opting for the 7 CP version have to write a term paper (15-20 pages, deadlines see below). The topic of the paper need not be identical or overlap with the topic of your oral presentation.
Oral Exam: If you decide to take an oral exam, we will together select 2 topics, which are disjoint from the topics of your presentation and term paper. Exam duration is 15-20 minutes.
Contact:
Prof. Dr. Bernd Möbius
Email
C7.2/4.10
0681/302-4500
Date | Topic | Papers / Slides / Questions | Presented by |
24.10. | Planning and organization, paper assignment | BM | |
07.11. | Overview: Intonation models | Botinis/etal:2001 pdf questions |
all |
14.11. | ToBI-based intonation synthesis | Jilka/etal:1999 pdf, Pierrehumbert:1981 pdf / slides | Georgis |
19.12. | Fujisaki's intonation model | Fujisaki:1988 pdf, Möbius:1995 pdf / slides | Hoang |
23.01. | Verbmobil and SmartKom prosody module | Batliner/etal:2000 pdf, Zeissler/etal:2006 pdf / slides | Saveleva |
23.01. | Prosodic models in ASR/ASU | Shriberg/Stolcke:2004 pdf / slides | Kröger |
30.01. | Quantitative alignment model | Santen/Mobius:2000 pdf | John |
30.01. | Discussion: Prosodic models | Batliner/Mobius:2005 pdf | BM/all |
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 = {Shriberg, 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} }