Benoit Favre

Education
Research
Experience
Skills
Teaching
Publications
Software

versions: English (pdf) Français (pdf) - updated: 2008-10-01 (sources)

ICSI, 1947 Center Street, Suite 600, Berkeley CA 94704, USA; +1 (510) 666 2930
favre.xyz@icsi.berkeley.edu (remove ".xyz" to obtain a valid address)
28 years old, French driving licence

Education

• 2007, PhD in computer science
  Laboratoire d'Informatique d'Avignon (LIA), University of Avignon (France)

• 2003, Master Degree in computer science
  Fundamental computer science, University of Avignon

• 2001, Bachelor's Degree in computer science
  mathematics and computer science engineering, networks speciality, University of Avignon

Research

• Postdoc research
  Sentence boundary detection in speech from various genre (broadcast news, broadcast conversations, meetings) and various languages (English, Arabic, Mandarin). Impact of sentence boundaries on subsequent information extraction tasks. Funded as part of the GALE project.

• PhD research work
  We explore the problematics of Automatic Speech Summarization applied to Spoken Document Retrieval to ease browsing of huge audio information databases. Specific areas studied:
  - spoken information extraction and structuring
  - extractive statistical summarization
  - user interfaces to spoken databases
  Work co-funded by the French Ministère de la Recherche et de l'Industrie and Thales Land & Joint Systems.

• Scientific Evaluation Campaigns
  - ESTER French spoken named entity extraction campaign in 2005
  - DUC and TAC text summarization campaign from 2006 to 2008
  - GALE machine translation evaluation in 2007 and 2008 (in charge of repunctuating speech in source language)

Work Experience

• 2007 to 2008 - Postdoc
  International Computer Science Institute, Berkeley (USA).
  

• 2004 to 2007 - Research Engineer
  Thales Land & Joint Systems Colombes (France), Multimedia Processing Laboratory.
  

• 2004 to 2006 - Web master of Association Francophone de la Communication Parlée (AFCP)
  Converted the website to Spip (php based content management portal)
  Involved in the French national project Technolangue
  

• 2001 to 2003 - Company creation project - Allegorian
  Automatic speech indexing to allow content access to multimedia documents.
  - studied the speech application market
  - developed a business model and communication strategy
  - created a distributed speech indexing platform and spoken information retrieval engine.
  

• 2002 - Final year project - LIA
  Adapted a spoken document retrieval engine to French.
  

• 2001 - 2nd year training, University of Avignon
  Ported to Linux a business management software for PARTS EQUIPMENT, a French reseller.
  

Technical Skills

• Programming: Perl, Java, C++, C, Python
  
  
• Machine Learning: AdaBoost, CRF, SVM
  
  
• Software Engineering: UML, Corba
  
  
• System: Linux/Unix, OSX
  
  
• Networks: Hardware, Administration, TCP/IP, Nat, Bind, Dhcp
  
  
• Databases: Postgres, Mysql, Access, Oracle
  
  
• Internet: Apache, HTML, PHP, Javascript, Ajax, Flash
  
  
• Languages: written and spoken scientific English, native French

Teaching

• 2003 to 2004 (80 hours) - Networks tutorials, BSc level, University of Avignon
  RJ45 cables, network traffic analysis, CISCO routers
  

• 2000 - Office computing tutorials, University of Avignon
  Taught MS Office to Biology and Literature students.
  

Publications

• Journals
  

  Mari Ostendorf, Benoit Favre, Ralph Grishman, Dilek Hakkani-Tur, Mary Harper, Dustin Hillard, Julia B. Hirschberg, Heng Ji, Jeremy G Kahn, Yang Liu, Evgeny Matusov, Hermann Ney, Elizabeth Shriberg, Wen Wang, Chuck Wooters, "Speech Segmentation and Its Impact on Spoken Language Technology", IEEE Signal Processing Magazine - 2008 (bib)
  

  Sebastien Cuendet, Dilek Hakkani-Tur, Elizabeth Shriberg, James Fung, Benoit Favre, "Cross-Genre Feature Comparisons for Spoken Sentence Segmentation", International Journal of Semantic Computing (IJSC), Volume 1, Issue 3; also published in IEEE International Conference on Semantic Computing (ICSC 2007), pp. 265-271, Irvine (USA) - 2007 (bib)
  

• International Conferences
  

  Benoit Favre, Dilek Hakkani-Tür, Slav Petrov, Dan Klein, "Efficient Sentence Segmentation Using Syntactic Features", to appear in Spoken Languge Technologies (SLT), Goa (India) - 2008 (bib)
  

  Gokhan Tur, Andreas Stolcke, Lynn Voss, John Dowding, Benoit Favre, Raquel Fernandez, Matthew Frampton, Michael Frandsen, Clint Frederickson, Martin Graciarena, Dilek Hakkani-Tür, Donald Kintzing, Kyle Leveque, Shane Mason, John Niekrasz, Stanley Peters, Matthew Purver, Korbinian Riedhammer, Elizabeth Shriberg, Jing Tien, Dimitra Vergyri, Fan Yang, "The CALO Meeting Speech Recognition and Understanding System", to appear in Spoken Languge Technologies (SLT), Goa (India) - 2008 (bib)
  

  Korbinian Riedhammer, Benoit Favre, Dilek Hakkani-Tür, "A Keyphrase Based Approach to Interactive Meeting Summarization", to appear in Spoken Languge Technologies (SLT), Goa (India) - 2008 (bib)
  

  Korbinian Riedhammer, Dan Gillick, Benoit Favre, Dilek Hakkani-Tür, "Packing the Meeting Summarization Knapsack", Interspeech, Brisbane (Australia) - 2008 (bib)
  

  Benoit Favre, Ralph Grishman, Dustin Hillard, Heng Ji, Dilek Hakkani-Tür, Mari Ostendorf, "Punctuating Speech for Information Extraction", IEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, Nevada (USA) - 2008 (bib)
  

  Sebastien Cuendet, Elizabeth Shriberg, Benoit Favre, James Fung, Dilek Hakkani-Tur, "An Analysis of Sentence Segmentation Features for Broadcast News, Broadcast Conversations, and Meetings", SIGIR 2007, Searching Spontaneous Conversational Speech (SSCS) workshop, pp. 37-43, Amsterdam (The Netherlands) - 2007 (bib)
  

  Florian Boudin, Benoit Favre, Frédéric Béchet, Marc El-Bèze, Laurent Gillard, Juan-Manuel Torres-Moreno, "The LIA-Thales summarization system at DUC-2007", DUC-NIST Proceedings Document Understanding Conference (DUC-2007), New York (USA) - 2007 (bib)
  

  Benoit Favre, Jean-François Bonastre, Patrice Bellot, "An Interactive Timeline for Speech Database Browsing", Interspeech 2007, Antwerp (Belgium) - 2007 (bib)
  

  Benoit Favre, Frédéric Béchet, Patrice Bellot, Florian Boudin, Marc El-Bèze, Laurent Gillard, Guy Lapalme, Juan-Manuel Torres-Moreno, "The LIA-Thales summarization system at DUC-2006", Document Understanding Conference Workshop, HLT-NAACL'06, New York (USA) - 2006 (bib)
  

  Benoit Favre, Frédéric Béchet, Pascal Nocéra, "Robust Named Entity Extraction from Spoken Archives", Proceedings of HLT-EMNLP'05, Vancouver (Canada) - 2005 (bib)
  

  Benoit Favre, Frédéric Béchet, Pascal Nocéra, "Mining Broadcast News data: Robust Information Extraction from Word Lattices", Proceeding of Eurospeech'05, Lisboa (Portugal) - 2005 (bib)
  

  Benoit Favre, Patrice Bellot, Jean-François Bonastre, "Information retrieval on mixed written and spoken documents", RIAO, Avignon (France), pp. 826-835 - 2004 (bib)
  

• French Conferences
  

  Benoit Favre, Jean-François Bonastre, Patrice Bellot, François Capman, "Accès aux connaissances orales par le résumé automatique", EGC'06, Lille (France) - 2006 (bib)
  

  Benoit Favre, Jean-François Bonastre, Patrice Bellot, "Recherche d'information dans un mélange de documents écrits et parlés", Journées d'Etude de la Parole (JEP), Fèz (Morocco) - 2004 (bib)
  

• Other publications
  

  Benoit Favre, "Résumé automatique de parole pour un accès efficace aux bases de données audio", PhD Thesis, University of Avignon (France) - 2007 (bib)
  

  Benoit Favre, "Indexation multimédia : caractérisation du déséquilibre entre les modalités texte et parole", Master Thesis, University of Avignon (France) - 2003 (bib)
  

  Download all entries in bibtex format here

Software

• icsiboost, an opensource implementation of BoosTexter
  Boosting decision stumps - http://code.google.com/p/icsiboost

• icsisumm, integer linear programming based summarization system
  participated to TAC'08 - http://code.google.com/p/icsisumm