Marcela Charfuelan

CV Research Teaching Publications

 

 
  Marcela Charfuelan

 
Researcher

   DFKI GmbH,
   Language Technology Lab
   Berlin Projektbüro,
  
Alt-Moabit 91c, D-10559 Berlin, Germany

  Tel +49 (0)30 238 95-1821
   Fax +49 (0)30 238 95-1810

  Email: Marcela.Charfuelan@dfki.de

AMCHO




CV:

Education:

2004
Ph.D. Telecommunication Engineering, Universidad Politécnica de Madrid (UPM), Madrid España.
1995
M.Sc. Electrical Engineering, Universidad de Los Andes, Bogotá Colombia.
1993
B.Sc. Electronic and Telecommunication Engineering, Universidad Del Cauca, Popayán Colombia.

Work Experience:

2007-
Researcher at Language Technology Laboratory of the German Research center for Artificial Inteligence (DFKI-LT), Berlin Germany.
2005-2007 Post-doc Researcher at Spoken Language Systems (LSV) (Lehrstuhl für Sprachsignalverarbeitung), Saarland University, Saarbrucken Germany.
2004-2005 Assistant Professor at Natural Interactive Systems Laboratory (NISLab), University of Southern Denmark (SDU), Odense Denmark.
2001-2004 Research Assistant at Natural Interactive Systems Laboratory (NISLab), University of Southern Denmark (SDU), Odense Denmark.

Fellowships:
1998-2000 Research Fellow at Speech Technology Group of GAPS-SSR Universidad Politécnica de Madrid (UPM) and Telefonica R&D of Spain.
1994-1995 Research Fellow at Electrical Engineering Department Universidad de Los Andes, Bogotá Colombia.


Research Interests:

- Speech signal processing and speech technology applications in general.
- Speech synthesis, in the context of  MARY TTS (in github: marytts).
- Parametric speech synthesis, using HMMs based on HTS and HTK for which I have developed the tutorial: HMMVoiceCreation for MARY TTS.
-
Expressive speech synthesis, prosody and voice quality analysis/synthesis of vocal social signals (politeness, dominance, stance) in the context of SSPNet project.
- Machine learning approaches for analysis/classification of speech signals (stress, cognitive load) in the context of Nifti project.
- Speech recognition, working with HTK and commercial sw.
- Speech recognition using microphone arrays, at LSV I have implemented a speech recognition system for microphone arrays based on the HTK-Toolkit and the Maximum Likelihood Beamforming approach.

- Spoken language dialogue systems, I have participated in the development of:
   - a dialogue system for using in car in the EU-project VICO-project.
   - a multimodal interactive dialogue system that enables communication between a human and an animated character,
conversational H.C. Andersen, in the EU-project NICE.


Teaching (past):

- Saarland University, tutorial sessions of Speech Technology course, Winter semester 2006-2007.
-
Saarland University, tutorial sessions of Pattern and Speech Recognition course, Winter semester 2005-2006.
- University of Southern Denmark, Acoustic Signal Processing course: NIS04, Autumn term 2004.


Publications and colaborations:


2013
- M. Charfuelan, G.J. Kruijff. Classification of speech under stress and cognitive load in USAR operations. In Proc. ICASSP 2013. Vancouver, Canada.
- M. Charfuelan, I. Steiner. Expressive speech synthesis in MARY TTS using audiobook data and EmotionML. In Proc. Interspeech 2013. Lyon, France.
- S. Pammi,M. Charfuelan. HMM-based sCost quality control for unit selection speech synthesis. In Proc. 8th ISCA Speech Synthesis Workshop (SSW8). Barcelona, Spain.
- M. Charfuelan, S. Pammi, I. Steiner. MARY TTS unit selection and HMM-based voices for the Blizzard Challenge 2013. In Proc. Blizzard Challenge 2013. Barcelona, Spain.

2012
- M. Charfuelan, M. Schröder. Correlation analysis of sentiment analysis scores and acoustic features in audiobook narratives. In Proc. ES3-LREC Workshop. Istanbul Turkey.
- M. Charfuelan. MARY TTS HMM-based voices for the Blizzard Challenge 2012. In Proc. Blizzard Challenge 2012. Portland, Oregon, USA.
- M. Charfuelan, G.J. Kruijff. Analysis of speech under stress and cognitive load in USAR operations. In Proc. IWSDS 2012. Paris, France.

2011
- M. Charfuelan, M. Schröder. The vocal effort of dominance in scenario meetings. In Proc. Interspeech. Florence Italy.
- M. Schröder, M. Charfuelan,  S. Pammi. I. Steiner. Open source voice creation toolkit for the MARY TTS Platform. In Proc. Interspeech. Florence Italy.
- M. Charfuelan, M. Schröder, S. Pammi. Classification of Listener Linguistic Vocalisations in Interactive Meetings. In Proc. European Signal Processing Conference (EUSIPCO-2011). Barcelona Spain.
- M. Charfuelan, M. Schröder. Investigating the prosody and voice quality of social signals in scenario meetings. In Proc. Affective Computing and Intelligent Interaction (ACCII). Memphis, USA.
- M. Charfuelan and Paul M. Brunet. Acoustic analysis of politeness and efficiency in a cooperative time-sensitive task. In Proc. 5th Workshop Emotion and Computing at German Conference on Artificial Intelligence (KI-2011). Berlin Germany.
- S. Pammi, M. Schröder, M. Charfuelan. Multidimensional meaning annotation of listener vocalizations for synthesis. In Proc. 5th Workshop Emotion and Computing at German Conference on Artificial Intelligence (KI-2011). Berlin Germany

2010
- M. Charfuelan, M. Schröder, I. Steiner. Prosody and voice quality of vocal social signals: the case of dominance in scenario meetings. In Proc. Interspeech. Makuhari, Japan.
- P. M. Brunet, M. Charfuelan, R. Cowie, M. Schröder, H. Donnan, E. Douglas-Cowie. Detecting politeness and efficiency in a cooperative social interaction. In Proc. Interspeech. Makuhari, Japan.
- I. Steiner, M. Schröder, M. Charfuelan, A. Klepp. Symbolic vs. acoustics-based style control for expressive unit selection. In Proc. Seventh ISCA Tutorial and Research Workshop on Speech Synthesis (SSW7). Kyoto, Japan.
- S. C. Pammi, M. Schröder, M. Charfuelan, O. Türk, I. Steiner. Synthesis of listener vocalisations with imposed intonation contours. In Proc. Seventh ISCA Tutorial and Research Workshop on Speech Synthesis. Kyoto, Japan.
- Pammi, S., Charfuelan, M., Schröder, M. Multilingual Voice Creation Toolkit for the MARY TTS Platform. In Proc. LREC 2010. Valettea, Malta.

2009
- Pammi, S., Charfuelan, M., Schröder, M. Quality control of automatic labelling using HMM-based synthesis. In Proc. ICASSP 2009, Taipei, Taiwan.

2008
- Marc Schröder, Marcela Charfuelan, Sathish Pammi and Oytun Türk. The MARY TTS entry in the Blizzard Challenge 2008. In Proc. Blizzard Challenge 2008, Brisbane, Australia.
- Marc Schröder, Patrick Gebhard, Marcela Charfuelan, Christoph Endres, Michael Kipp, Sathish Pammi, Martin Rumpler and Oytun Türk . Enhancing Animated Agents in an Instrumented Poker Game. In Proc. KI 2008 (LNAI 5243, pp. 316-323). Kaiserslautern, Germany, Springer.
- Patrick Gebhard, Marc Schröder, Marcela Charfuelan, Christoph Endres, Michael Kipp, Sathish Pammi, Martin Rumpler and Oytun Türk. IDEAS4Games: Building Expressive Virtual Characters for Computer Games. In Proc. IVA (Vol. 5208, pp. 426-440). Tokyo, Japan, Springer.

2005
- Andrea Corradini, Manish Mehta and Marcela Charfuelan. Interacting with an Animated Conversational Agent in a 3D Graphical Setting.  In Proc. Workshop on Multimodal Interaction for the Visualization and Exploration of scientific data at the International Conference on Multimodal Interfaces (ICMI'05), October 3-6, Trento (Italy), pp. 63-70.
- Andrea Corradini, Manish Mehta, Niels-Ole Bernsen and Marcela Charfuelan. Animating an Interactive Conversational Character for an Educational Game System. In Proc. International Conference on Intelligent User Interfaces, pp. 183-190, January 9th-12th, San Diego (CA, USA).


2004
- Niels Ole Bernsen, Marcela Charfuelan, Andrea Corradini, Laila Dybkjaer, Thomas Hansen, Svend Kiilerich, Mykola Kolodnytsky, Dmytro Kupkin and Manish Mehta. Conversational H. C. Andersen. First prototype description. In Proc. Tutorial and Research Workshop on Affective Dialogue Systems (ADS04), LNAI 3068, Kloster Irsee, Germany, pp. 305-308.

- Niels Ole Bernsen, Marcela Charfuelan, Andrea Corradini, Laila Dybkjaer, Thomas Hansen, Svend Kiilerich, Mykola Kolodnytsky, Dmytro Kupkin and Manish Mehta. First prototype of conversational H.C. Andersen. In Proc. International Working Conference on Advanced Visual Interfaces (AVI 2004), Gallipoli (Lecce), Italy, pp. 458-461.

2003
- Marcela Charfuelan. Evaluation Techniques of Spoken Language Dialogue Systems (Spanish). (2003).  PhD Thesis, October 2003, Universidad Politecnica de Madrid.

- Marcela Charfuelán and Niels Ole Bernsen . A Task and Dialogue Model Independent Dialogue Manager. In Proc. 4th International Conference on Recent Advances in Natural Language Processing (RANLP), Borovets, Bulgaria.
- Marcela Charfuelán, Holmer Hemsen and Marnie Lai. Multi-lingual Response Generator for Spoken Dialogue Systems: Database Approach. In Proc. 4th International Conference on Recent Advances in Natural Language Processing (RANLP), Borovets, Bulgaria.

2002
- Marcela Charfuelán, Luis Hernández Gómez, Cristina Esteban López, Holmer Hemsen. A XML-based tool for evaluation of SLDS. In Proc. 3th International Conference on Language Resources and Evaluation LREC-2002, Las Palmas Canary Islands, Spain, 29-31 May 2002.


2000
- Marcela Charfuelán Oliva, Cristina Esteban, José Relaño, M. Carmen Rodríguez Gancedo, Luis Hernández Gómez. A General Evaluation Framework to Assess Spoken Language Dialogue Systems: Experience with Call Center Agent Systems. In Proc. 1st workshop on Robust Methods in Analysis of Natural language Data (ROMAND), Department of Computer Science, Swiss Federal Institute of Technology, Lausanne Switzerland, October 19-20 2000.
- Marcela Charfuelán Oliva, José Relaño, M. Carmen Rogríguez Gancedo, Daniel Tapias Merino, Luis Hernández Gómez. Dialogue Annotation for Language Systems Evaluation. In Proc. 2nd International Conference on Language Resources and Evaluation LREC-2000, Athens, Greece, 31 May - 2 June 2000.

1999
- José Relaño Gil, Daniel Tapias, Maria C. Rogríguez, Marcela Charfuelán, Luis Hernández Gómez. Robust and Flexible Mixed-Initiative Dialogue for Telephone Services. In Proc. Ninth Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of EACL, June 1999, University of Bergen, Bergen, Norway, 287-290.


1996
- M. Charfuelan, N. Correa. Reconocimiento de voz continua, (Spanish), (Continuous Speech Recognition). Memorias de las IX Jornadas de Electrónica y Telecomunicaciones, ACIEM (Asociación Colombiana de Ingenieros Electricistas, Mecánicos, Electrónicos y afines), Bogotá Colombia, Julio de 1996.


1995
- Marcela Charfuelán, Técnicas de reconocimiento de voz continua, estrategia de reconocimiento de palabras conectadas, (Spanish), (Continuous Speech Recognition Techniques, Connected-Word Recognition Strategy) . Memorias del Simposio de Tratamiento de Señales, Tratamiento de imágenes y Visión artificial, Departamento de Ingeniería Eléctrica, Universidad de Los Andes. Bogotá Colombia, Septiembre de 1995