Arif Khan

Arif Khan

Doctoral Researcher in Saarland University

Download Résumé

About Me

I am a doctoral student in the Multimodal Speech Processing group at Multimodal Computing and Interaction (M2CI) under the supervision of Dr. Ingmar Steiner. Before that, I did my M.Sc Computer Science from Saarland University and B.Sc Computer Science from Islamia College Peshawar, Pakistan.

My research interests include:

  • Speech segmentation
  • Segmentation behaviour analysis
  • Acoustic modeling
  • Audio Analysis
  • Automatic speech recognition

Education

Ph.D Computer Science, Jun 14 — Present

Saarland University, Saarbücken, Germany

M.Sc Computer Science, Apr 10 — Dec 13

Saarland University, Saarbücken, Germany

B.Sc (Hons) Computer Science, Jan 03 — Dec 06

Islamia College University, Peshawar, Pakistan

Work Experience

Doctoral Researcher, Jun 14 — Present

DFKI, Language Technology Lab, Saarbücken, Germany

  • Multimodal speech segmentation
  • Human segmentation behaviour analysis
  • Automatic speech recognition
  • Acoustic modeling for speech recognition
  • Feature fusion to combine different modalities

Internship, Sep 12 — Dec 12

SAP AG, Sankt Leon-Rot, Germany

  • On Demand Solutions
  • Develop and enhance prototype for better software problems reporting
  • Embedded support for customers

Research Assistant, Mar 11 — Aug 11

M2CI, Saarbücken, Germany

  • Java programming
  • Assist in research work (WisNetGrid project)
  • Information extraction and ontology engineering

Teaching (Tutor)

Statistical Natural Language Processing, Apr 13 — Aug 13

Saarland University

  • Conduct tutorial sessions
  • Make exercise sheets
  • Correct solutions and discuss problems

Software Engineering, Oct 10 — Feb 11

Saarland University

  • Supervise student projects
  • Conduct tutorials for the software engineering lecture

Spoken Dialog Systems for Elevator Control, Apr 15 — Aug 15

Saarland University

  • Assist student groups for the project
  • Train acoustic model for the elevator

Publications

Arif Khan and Ingmar Steiner. Fusing gaze data and spectrogram image features for automatic phonetic segmentation. In 30th Conference on Electronic Speech Signal Processing (ESSV), Dresden, Germany, March 2019. accepted. [bib]

Arif Khan, Ingmar Steiner, Yusuke Sugano, Andreas Bulling, and Ross Macdonald. A multimodal corpus of expert gaze and behavior during phonetic segmentation tasks. In11th Language Resources and Evaluation Conference (LREC), pages 4277–4281, Miyazaki, Japan, May 2018. [bib, poster, pdf]

Arif Khan and Ingmar Steiner. Qualitative evaluation and error analysis of phonetic segmentation. In 28th Conference on Electronic Speech Signal Processing (ESSV), pages 138–144, Saarbrücken, Germany, March 2017. [bib, pdf]

Arif Khan, Ingmar Steiner, Ross Macdonald, Yusuke Sugano, and Andreas Bulling. Scene viewing and gaze analysis during phonetic segmentation tasks. In 18th European Conference on Eye Movements (ECEM), Vienna, Austria, August 2015. [bib, poster]

Oliver Ohneiser, Hartmut Helmke, Heiko Ehr, Hejar Gürlük, Michael Hoessl, Thorsten Mühlhausen, Youssef Oualil, Marc Schulder, Anna Schmidt, Arif Khan, and Dietrich Klakow. Air traffic controller support by speech recognition. In 5th International Conference on Applied Human Factors and Ergonomics (AHFE), At Kraków, Poland, 07 2014. [pdf]

Anna Schmidt, Youssef Oualil, Oliver Ohneiser, Matthias Kleinert, Marc Schulder, Arif Khan, Hartmut Helmke, and Dietrich Klakow. Context-based recognition network adaptation for improving on-line ASR in air traffic control. In Spoken Language Technology Workshop (SLT), pages 13–18. IEEE, 2014. [pdf, doi]

Arif Khan. Automatic Speech Recognition techniques to improve Air Traffic Control management. Master thesis, LSV, Saarland University, 2014.

Contact

arifkhan AT coli.uni-saarland DOT de

+49 (0) 681 302 70022

Campus C7.4, Room 2.03
Saarland University
66123 Saarbrücken,
Germany