Curriculum Vitae

Short resume - CV: click here

Extended resume - CV: click here

Education

• Ph.D in Computer Science, (EPFL) École Polytechnique Fédérale de Lausanne, 2024 (expected)
• M.S. in Mechatronic Engineering, Universidad de Oviedo, 2019
• B.S. in Mechatronic Engineering, Universidad Autonoma del Caribe, 2016

Work experience

• January 2020 - Ongoing: Ph.D. Student in Computer Science
  • Idiap Research Institute and EPFL (Martigny, Switzerland)
  • Topics: Automatic Speech Recognition and Natural Language Processing
  • Current Projects: ATCO2, HAAWAII, Skysoft, Eurocontrol
• July-September 2023 - Machine Learning Engineer—Internship
  • Apple, AI/ML Team, Cambridge, MA, USA
  • Topics: Working on discriminative training of language models to improve automatic speech recognition (ASR) performance on tail named-entity data
  • Transformer-based language modeling for production-level ASR systems
• April–July 2023 - Applied Scientist—Internship
  • Amazon, Amazon Web Services (AWS), Seattle, WA, USA
  • Topics: Research on dual speech-to-text Translation (ST) and Transcription (ASR) for conversational speech
  • Serialized output training (conditioned with special tokens, akin to Whisper) for robust multilingual ST and ASR
  • Our system is aware of speaker turns and overlapped speech, improving BLEU and WER performance
• January-December, 2019: Master Thesis, Research Assitant
  • Research Institute Femto-ST (Besancon, France)
  • Duties included: Computer Vision & Mechatronics Engineer
  • Project: SBRA-“Smart BRA” EU project
• January 2014 - Ongoing: Mechatronics Research Group Member
  • Universidad Autonoma del Caribe (Barranquilla, Colombia)
  • Duties included: B.Sc supervisor, active member
• January 2016 - August 2017: Research and Innovation Deparment: Assistant
  • Universidad Autonoma del Caribe (Barranquilla, Colombia)
  • Duties included: Research groups and metrics tracking, (2 patents holder)

Skills

• Technical (IT) Skills:
  • Automatic Speech Recognition (ASR)
  • Natural Language Processing (NLP)
  • Languages: Python
  • Others: Jupyter, Google Colab, Bash, LaTeX
  • Softwares: Matlab, Solidworks, Proteus, Eagle, LabView
• Soft Skills:
  • Teamwork
  • Communication
  • Self-management
  • Problem Solving

Hobbies

• Cooking
• Reading (currently: The Expanse - novel series)
• Coffee Brewing
• Traveling and Hiking

Publications

A survey of breast cancer screening techniques: thermography and electrical impedance tomography

Zuluaga-Gomez, J., Zerhouni, N., Al Masry, Z., Devalland, C. and Varnier, C., 2019. A survey of breast cancer screening techniques: thermography and electrical impedance tomography. Journal of medical engineering & technology, 43(5), pp.305-322.

A portable breast cancer detection system based on smartphone with infrared camera

Ma, J., Shang, P., Lu, C., Meraghni, S., Benaggoune, K., Zuluaga, J., Zerhouni, N., Devalland, C. and Al Masry, Z., 2019. A portable breast cancer detection system based on smartphone with infrared camera. Vibroengineering PROCEDIA, 26, pp.57-63.

Techniques for water disinfection, decontamination and desalinization: A review

Zuluaga-Gomez, J., Bonaveri, P., Zuluaga, D., Álvarez-Peña, C. and Ramirez-Ortiz, N., 2020. Techniques for water disinfection, decontamination and desalinization: A review. Desalin. WATER Treat, 181, pp.47-63.

Automatic Speech Recognition Benchmark for Air-Traffic Communications

Zuluaga-Gomez, J., Motlicek, P., Zhan, Q., Veselý, K., Braun, R. (2020) Automatic Speech Recognition Benchmark for Air-Traffic Communications. Proc. Interspeech 2020, 2297-2301, doi: 10.21437/Interspeech.2020-2173.

Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models

Madikeri, S., Tong, S., Zuluaga-Gomez, J., Vyas, A., Motlicek, P. and Bourlard, H., 2020. Pkwrap: a pytorch package for lf-mmi training of acoustic models. arXiv preprint arXiv:2010.03466.

A CNN-based methodology for breast cancer diagnosis using thermal images

Zuluaga-Gomez, J., Al Masry, Z., Benaggoune, K., Meraghni, S. and Zerhouni, N., 2021. A CNN-based methodology for breast cancer diagnosis using thermal images. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 9(2), pp.131-145.

Automatic Call Sign Detection: Matching Air Surveillance Data with Air Traffic Spoken Communications

Zuluaga-Gomez, J.; Veselý, K.; Blatt, A.; Motlicek, P.; Klakow, D.; Tart, A.; Szöke, I.; Prasad, A.; Sarfjoo, S.; Kolčárek, P.; Kocour, M.; Černocký, H.; Cevenini, C.; Choukri, K.; Rigault, M.; Landis, F. Automatic Call Sign Detection: Matching Air Surveillance Data with Air Traffic Spoken Communications. Proceedings 2020, 59, 14. https://doi.org/10.3390/proceedings2020059014

Boosting of Contextual Information in ASR for Air-Traffic Call-Sign Recognition

Kocour, M., Veselý, K., Blatt, A., Gomez, J.Z., Szöke, I., Černocký, J., Klakow, D., Motlicek, P. (2021) Boosting of Contextual Information in ASR for Air-Traffic Call-Sign Recognition. Proc. Interspeech 2021, 3301-3305, doi: 10.21437/Interspeech.2021-1619.

Contextual Semi-Supervised Learning: An Approach to Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems

Zuluaga-Gomez, J., Nigmatulina, I., Prasad, A., Motlicek, P., Veselý, K., Kocour, M., Szöke, I. (2021) Contextual Semi-Supervised Learning: An Approach to Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems. Proc. Interspeech 2021, 3296-3300, doi: 10.21437/Interspeech.2021-1373.

Grammar Based Identification Of Speaker Role For Improving ATCO And Pilot ASR

Prasad, A., Zuluaga-Gomez, J., Motlicek, P., Ohneiser, O., Helmke, H., Sarfjoo, S. and Nigmatulina, I., 2021. Grammar Based Identification Of Speaker Role For Improving ATCO And Pilot ASR. arXiv preprint arXiv:2108.12175.

Improving callsign recognition with air-surveillance data in air-traffic communication

Nigmatulina, I., Braun, R., Zuluaga-Gomez, J. and Motlicek, P., 2021. Improving callsign recognition with air-surveillance data in air-traffic communication. arXiv preprint arXiv:2108.12156.

Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition

Zhan, Q.; Xie, X.; Hu, C.; Zuluaga-Gomez, J.; Wang, J.; Cheng, H. Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition. Electronics 2021, 10, 3172. https://doi.org/10.3390/electronics10243172

A two-step approach to leverage contextual data: speech recognition in air-traffic communications

Nigmatulina, Iuliia and Zuluaga-Gomez, Juan and Prasad, Amrutha and Saeed Sarfjoo, Seyyed and Motlicek, Petr. (2022). A two-step approach to leverage contextual data: Speech recognition in air-traffic communications. ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing, 6282–6286

BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications

Juan Zuluaga-Gomez, Seyyed Saeed Sarfjoo, Amrutha Prasad, Iuliia Nigmatulina, Petr Motlicek, Karel Ondrej, Oliver Ohneiser, Hartmut Helmke, 2022. BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications. 2022 IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar.

IDIAPers - Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach

Burdisso, Sergio and Zuluaga-Gomez, Juan and Villatoro-Tello, Esau and Fajcik, Martin and Singh, Muskaan and Smrz, Pavel and Motlicek, Petr, 2022. IDIAPers - Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach. The 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE - EMNLP 2022). Association for Computational Linguistics

IDIAPers - Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model

Fajcik, Martin and Singh, Muskaan and Zuluaga-Gomez, Juan and Villatoro-Tello, Esau and Burdisso, Sergio and Motlicek, Petr and Smrz, Pavel, 2022. IDIAPers - Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model. The 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE - EMNLP 2022). Association for Computational Linguistics

How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications

Juan Zuluaga-Gomez, Amrutha Prasad, Iuliia Nigmatulina, Saeed Sarfjoo, Petr Motlicek, Matthias Kleinert, Hartmut Helmke, Oliver Ohneiser, Qingran Zhan, 2022. How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications. 2022 IEEE Spoken Language Technology Workshop (SLT), Doha, Qatar.

Scholarships, Awards, Distinctions

• 1st place Hackaton, 2020
  • International Create Challenge Winner (1st place)
  • Special HealthTech Award by Groupe Mutuel
• Erasmus Mundus Scholarship, 2017
  • Awarded by European Union, EACEA
  • Program: Joint Master Degree in Mechatronic Engineering - EU4M
• Research Scholarship: visits in Germany, 2014
  • Awarded by: German Academic Exchange Service (DAAD)
  • Program: visits in several research labs in Germany
• Scholarship: 2015 and 2017
  • Awarded by: Universidad Autonoma del Caribe
  • Reason: to attend XV and XVI World Summit of Nobel Peace Laureates in Spain (2015) and Colombia (2017)
• Honor Roll: 2012 - 2015
  • Awarded by: Universidad Autonoma del Caribe
  • Reason: 6 times Honor Roll (4.5/5.0) - grade score distinction

Talks

An introduction to speech-based technologies for Natural Language Processing applications

June 03, 2021

Talk at Mexican NLP Summer School 2021, Ciudad de Mexico, Mexico