Dr. Timo Baumann
Researcher and instructor in speech processing, in particular incremental processing for responsive spoken dialogue interaction, at Universität Hamburg.
- mail: baumannÄŦinformatik.uni-hamburg.de
- skype: timobaumann
- tel: +49 40 428832360
- office: GHC 5405, Carnegie Mellon University
- consultation hours: please make an appointment by e-mail
- 2017-02: I'm leaving Hamburg heading for Pittsburgh!
we're hiring, I'm looking forward to your application!
- 2016-12: Sven Barske of the local station Hamburg 90,3 (which is part of Norddeutscher Rundfunk) recently interviewed me on Adobe Voco.
- 2016-11: I'm running a listening/rating experiment and I sincerely appreciate your participation. For the moment this is German only.
- 2016-11: I'm looking forward to seeing you in Osaka, at Coling, LT4DH or YRSNLP!
- 2016-10: My paper (together with Burkhard Meyer-Sickendiek) describing an application of speech technology to free verse poetry is accepted for LT4DH. (UPDATE: Volkswagenstiftung will fund a three-year project to further extend this research.)
- 2016-10: I'll attend a Dagstuhl meeting on barking and meowing in November, yay!
- 2016-10: Christine and I will host gorup in the trial study week for prospective students -- update: our group won the competition, see the video!
- 2016-09: Arnes and my paper on incremental and predictive parsing for language modelling is accepted at COLING. Yay! We show how incremental parsing can improve LM perplexity on the Billion Word Corpus by ~6% with little compuational overhead and while allowing online decoding.
- 2016-08: I spoke at WikiCon 2016 about the Spoken Wikipedia Corpus and we had really interesting discussions on integrating better reading capabilities into MediaWiki.
- 2016-07: Marcel Rohde's Bachelor work on navigating the Spoken Wikipedia resulted in a paper at SLPAT. Yay! Update: also see the videos.
- older news
- 2016-05: Kolja Kirsch's Bachelor work not only received the 1st prize in the Informatik EXPO 2015 but he also got it accepted as a long paper at Mensch und Computer 2016, Germany's most important HCI conference. Congratulation! (There's also a Youtube-Video.)
- 2016-04: Christine and I will host a Girls' Day group next week on Spoken Dialogue Systems.
- 2016-03: I'll be at LREC in May presenting our paper on the Spoken Wikipedia Corpus.
- 2016-02: I'm teaching the MSc course on speech processing and co-teaching a project on subtitling this summer.
- 2015-11: Join us at the Science Fair in Hamburg!
- 2015-11: Casey's, Julian's, David's and my paper that compares incremental performance of ASR systems has been accepted at IWSDS. Yay!
- 2015-10: I'll be teaching an ESSLLI 2016 introductory course on Incremental Speech and Language Processing for Interactive Systems together with Arne Köhn.
- 2015-09: Listen to Maël and me live-interviewed on Interspeech Radio on Monday morning (or tune into the Podcast afterwards)
- 2015-02: I will be teaching two "Proseminare" next semester: Speech Processing and Software Development Helpers. Please follow the links for the full announcements.
- 2015-01: I attended a workshop on science journalism at the Klaus-Tschira-Foundation last week and learned how press releases lead to reports first in local news, then specialized papers, and finally public radio. Too bad only my former supervisor is mentioned in the press release -- more details and authors in the original research paper.
- 2014-12: German Hackers are meeting in Hamburg between Christmas and New Year's. I'll give a talk on our student group project's results with sub-titling CCC talks.
- 2014-11: I'll be giving a talk at gipsa-lab in Grenoble on December 11th. Hope to see you there!
- 2014-09: I'll be in Singapore during Interspeech and then give an invited talk at a small workshop organized by Prof. Kai Yu in Shanghai afterwards. Hope to see you there!
- 2014-08: My stay in New York is great, and both AT&T and Yahoo!Labs seem to be very nice places to work in industry. However, I'm also looking forward to the calm atmosphere and cold weather back in Hamburg...
- 2014-06: My Interspeech submission has been accepted -- yay!
- 2014-06: I'll be speaking at the TU Darmstadt colloquium next Wednesday. Looking forward to seeing you there!
- 2014-05: I've booked my flight and will be staying in New York during all of August. Let me know if we should meet&greet there!
- 2014-04: Johannes Twiefel's (and my, as one of the supervisors) AAAI 2014 submission has been accepted -- we're going to revolutionize your Google ASR experience in limited domains (for now non-incrementally, but stay tuned).
- 2014-02: My paper on "Decision Tree Usage for Incremental Parametric Speech Synthesis" has been accepted for ICASSP 2014 -- yay, I get to travel to Florence!
- 2014-01: I have received one of 10 PostDoc awards by Daimler-und-Benz-Stiftung for a project on further developing incremental spoken dialogue processing systems. Yay!
- 2014-01: The German Science Year 2014 focuses on Digital Society and teachers and other educators can now invite me as an expert to speak at their school. I hope to raise broader interest in dialogue and computerized spoken language processing in high school students this way.
- 2013-12: I gave an InproTK hands-on programming tutorial in Bielefeld yesterday. Thanks to the DSG group for hosting me. The tutorial exercises, which give a good introduction to InproTK, are on Sourceforge.
- 2013-11: I participated (together with Christine and Arne Köhn) in Hamburg's Science Night 2013. This was one of our posters.
- 2013-09: our tutorial on incremental processing at Interspeech 2013 was a huge success! Slides can be found here
- 2013-07: Yay, David Schlangen's and my paper for the speech synthesis workshop has been accepted: "Interactional Adequacy as a Factor in the Perception of Synthesized Speech"
- 2013-06: Yay, David Schlangen's and my SigDial short-paper has been accepted: "Open-ended, Extensible System Utterances Are Preferred, Even If They Require Filled Pauses"
- 2013-05: what an exciting week: I defended my thesis on Thursday and got married on Saturday! Off to a week of vacation...
- 2013-04: I have submitted my thesis, at last!
- 2013-03: A poster describing our hybrid (incremental/non-incremental) prototype for playing Pentomino was presented last week at the DGfS computational linguistics poster session and will be presented in a talk next week at ESSV!
- 2013-02: David Schlangen and I will have an Interspeech Tutorial on Incremental Spoken Dialogue Processing (based on InproTK, of course)
- 2012-11: Rabih Hamadeh has turned in his thesis on Machine Learning methods for incremental ASR smoothing. Well done!
- 2012-10: The workshop on Architectures for Conversationally Competent SDS which I organized on 5th/6th October was a tremendous success, both scientific as well as community-wise and culinary. I will (have to) write up a documentation of the workshop in the upcoming weeks, some results are linked to in the programme.
- 2012-09: Last year's SDS project resulted in an exiting prototype for playing Pentomino using a hybrid system consisting of both standard techniques (using DialogOS) and incremental processing (using InproTK); I made a video out of some example interactions to show some of its highligths
- 2012-06: The workshop on Architectures for Conversationally Competent SDS is starting to take shape: Kristinn Thórisson will be the keynote speaker and the event will take place 5th/6th October. More news are at the link.
- 2012-06: Our (David Schlangen's and my) paper on "Evaluating Prosodic Processing for Incremental Speech Synthesis" was accepted to be presented at Interspeech 2012 in Portland, USA. Yay! Now, all I have to do is win in the lottery...
- 2012-06: I've been awarded a DAAD travel grant to attend ACL in Korea where I'll be presenting my work on incremental speech synthesis. yay!
- 2012-05: Last week's Girl's Day was a full success, with 12 young ladies building dialogue systems that you can discuss your schoolday with or that counsel you on your homework.
- 2012-05: Our (Hendrik Buschmeier's, Benjamin Dosch's, David Schlangen's, Stefan Kopp's and my) paper on Adaptive Information Presentation Through Incremental Language Generation and Incremental Speech Synthesis was accepted to be presented at SIGdial 2012. This features my work on incremental speech synthesis which I'm really proud of
- 2012-04: Our (Kris Lohmann's and Ole Eichhorn's and my) paper on Generating Situated Assisting Utterances for Tactile Map Exploration was accepted to be presented at SLPAT 2012. We hope to get funding for Ole, who is a very bright Bacchelor student in Human Machine Interaction, to present the work in Montreal, CA.
- 2012-04: Our (David Schlangen and my) paper on incremental speech synthesis was accepted to be presented as a system demonstration at ACL 2012 in Korea. I hope this convinces DAAD to fund my travel to ACL/SIGdial/YRRSDS which are all co-located.
- 2012-03: I'm organizing a small workshop on Architectures for Conversationally Competent Dialogue Systems sponsored by the Körber-Fonds for Young Scientists, more information will become available shortly
- 2012-03: I'm now associated to the CINACS graduate school.
Why do we speak how we speak when we just speak to speak?
And how can we model systems to do the same?
A (slightly longer) research statement
- I maintain InproTK, the incremental dialogue processing toolkit, which is being used in multiple research labs around the world for building incremental spoken dialogue systems.
- Together with David Schlangen, I gave an Interspeech tutorial on incremental processing in 2013 which was a great success. Slides can be found here. Exercises from a more recent introduction to InproTK are on Sourceforge.
- I've organized the Workshop on Architectures for Conversationally Competent Spoken Dialogue Systems 2012 in Hamburg, Germany. The purpose of the workshop was to bring young researchers in the field together to talk about upcoming challenges in developing highly interactive and natural dialogue systems/virtual agents/conversational systems.
- I've co-organized the Young Researcher's Roundtable on Spoken Dialogue Systems 2012 in Seoul, Korea
- I've been reviewing for LREC 2010-2016, IJCNLP 2011,2015, (E)ACL 2015-2017, EMNLP 2016, Coling 2016, AAAI 2012, SigDIal 2013-2016, SemDial 2014, BEA 2014-2016, ICMI 2013-2016, Interspeech 2015-2016, ICASSP 2017, HRI 2015-2016, AutomotiveUI 2014-2015, ACM TiiS, TALLIP, SoRo, KnoSys, CSL, LREV, and multiple smaller events
- Next winter term 2016
- Logics Programming Exercises
- Practical Course ("Praktikum") on Using Speech Processing Software (BSc)
- Summer term 2016
- Fall/winter term 2015/16
- Summer term 2015
- Fall/winter term 2014/15
- two practical courses in Logics Programming: Wednesday 12-14 and 14-16, both in D-129.
- a project (BSc and MSc) developing an an open-source application for semi-automatic subtitling.
- I did not have to teach in the summer term 2014
- Fall/winter term 2013/2014
- I'm taught two practical courses in Logics Programming: Wednesday 12-14 and 14-16, both in D-220.
- Summer term 2013
- Fall/winter term 2012/2013
- Summer term 2012
- Fall/winter term 2011/2012
- Seminar Spoken Dialogue Systems (Master of Informatics, Mo. 14-16); together with Prof. Menzel's lectures on Spoken Language Processing this "Integriertes Seminar" forms the module Language Processing in the curriculum for master students
- Project Spoken Dialogue Systems (Bachelor of Informatics, Do. 14-17; 1st part); you'll need to attend the second part of this project next semester to get full credit
Currently, I am supervising
Jula Menck's BSc thesis on speech characteristics in the Spoken Wikipedia Corpus,
Alexandra Krah's BSc thesis on temporal elasticity of speech sounds in variable-rate speech,
Tim Krämer's MSc thesis which aims at bringing better Spoken Wikipedia browsing to the real Wikipedia.
I have previously co-supervised
Natalia Orlova's MSc thesis on the combination of multiple incremental speech recognizers,
Marcel Rohde's BSc thesis on a Spoken Wikipedia Browser,
Valentin Strauss' BSc thesis on incremental post-processing of Google's ASR results,
Florian Stegen's BSc thesis on long audio alignment for the Spoken Wikipedia,
Jonathan Werner's BSc thesis on keyword spotting in lecture transcriptions,
Sven Zimmer's BSc thesis on build tools for scientific software development,
Anne Rubruck's MSc thesis on decomposing semantic annotations into lexical semantics,
Kolja Kirsch's BSc thesis on semi-automatic page-turning for piano sheet music,
Jiyan Jonsdotter's BSc thesis on applying incremental spoken output to navigation systems,
Engelke Eschner's diploma thesis on NLG for transit schedules,
Sören Nykamp's BSc thesis on incremental processing in interactive storytelling,
Johannes Twiefel's MSc thesis on improving Google's ASR using phonetic post-processing techniques given domain knowledge,
Anita Eisenhaber's BSc thesis on sentiment analysis in social media statements (tweets, etc.),
Svenja Neef's BSc thesis on analyzing the incremental properties of Android's ASR and integrating it with InproTK,
Ole Eichhorn's BSc thesis on incremental speech synthesis integration into the VAVETaM system,
and Rabih Hamadeh's MSc thesis on optimizing incremental ASR hypotheses.
I actively encourage students to go abroad! I successfully talked
Maike Paetzel into visiting ICT as a summer intern in 2013 to work with David DeVault (which resulted in a publication at LREC 2014),
and Arne Köhn is visiting ICT as a summer intern in 2014 to work with Kenji Sagae on incremental parsing.
Sven Mutzl approached me regarding an internship opportunity in Shanghai which I helped to set up in collaboration with Kai Yu at Shanghai Technical University.
Siva Meenakshi Renganathan from Anna University (Chennai) visited our lab as a summer intern in 2014 to work on exploiting Spoken Wikipedia data for speech research.
Under construction: Timo's assessment criteria
for theses (and, to a lesser degree, seminar papers). See also: Timo's advice on how to write a good thesis