ⓘ More details here
Ina Kodrasi is heading the Signal Processing for Communication Group at Idiap Research Institute, which focuses on establishing signal processing and machine learning approaches to tackle a wide range of challenges arising in human communication.
She received the Master of Science degree in Communications, Systems and Electronics in 2010 from Jacobs University Bremen, Germany and the PhD degree in 2015 from the University of Oldenburg, Germany. From 2010 to 2015 she worked as a researcher at the Signal Processing Group of the University of Oldenburg. From 2010 to 2011 she was also with the Fraunhofer Institute for Digital Media Technology (IDMT), Project group Hearing, Speech and Audio Technology in Oldenburg where she worked on microphone array beamforming. From 2015 to 2017 she was a postdoctoral researcher at the Signal Processing Group of the University of Oldenburg in the field of speech dereverberation and noise reduction. She joined Idiap Research Institute in December 2017, where she now leads the Signal Processing for Communication Group.
- P. Janbakhshi, I. Kodrasi, "Adversarial-free speaker identity-invariant representation learning for automatic dysarthric speech classification," in Proc. Annual Conference of the International Speech Communication Association, Incheon, Korea, Sept. 2022.
- P. Janbakhshi, I. Kodrasi, H. Bourlard, "Subspace-based learning for automatic dysarthric speech detection," in IEEE Signal Processing Letters, vol. 28, pp. 96-100, Dec. 2020.
- I. Kodrasi, H. Bourlard, "Spectro-temporal sparsity characterization for dysarthric speech detection," in IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 28, pp. 1210-1222, May 2020.
- I. Kodrasi, S. Doclo, "Analysis of eigenvalue decomposition-based late reverberation power spectral density estimation," in IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 6, pp. 1106-1118, June 2018. *Best Paper Award, VDE Information Technology Society*
- B. Cauchi, I. Kodrasi, R. Rehr, S. Gerlach, A. Jukic, T. Gerkmann, S. Doclo, S. Goetze, Combination of MVDR beamforming and single-channel spectral processing for enhancing noisy and reverberant speech, EURASIP Journal on Advances in Signal Processing, 2015:61
- I. Kodrasi, S. Goetze, S. Doclo, Regularization for Partial Multichannel Equalization for Speech Dereverberation, IEEE Trans. Audio, Speech and Language Processing, vol. 21, no. 9, pp. 1879-1890, Sep. 2013
Selected Academic Activities
- Associate Editor - EURASIP Journal on Audio, Speech, and Music Processing (2022 - Ongoing)
- ArXiv Moderator - Electrical Engineering and Systems Science (2021 - Ongoing)
- Elected Member of the IEEE Technical Committee of Audio and Acoustic Signal Processing (2019 - Ongoing)
- Steering Committee Member of the IEEE SPS program: ME-UYR - Mentoring Experiences for Underrepresented Young Researchers (2019 - Ongoing)
- Area Chair for the Annual Conference of the International Speech Communication Association (Interspeech) (2021, 2022, 2023)
- Area Chair for the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2021, 2022, 2023)
- Area and Publicity Chair for the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (2021)
- Organizing Committee Member for the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (2021)
- Ph.D., Thesis title: "Dereverberation and noise reduction techniques based on acoustic multi-channel equalization", University of Oldenburg, Germany (Sep 2010 - Dec 2015)
- M.Sc. in Communications, Systems, and Electronics, Thesis title: "Sensor position optimization for superdirective beamforming", Jacobs University Bremen, Germany (Sep 2008 - Aug 2010)
- B.Sc. in Electrical Engineering and Computer Science, Thesis title: "Independent component analysis for blind source separation", Jacobs University Bremen, Germany (Sep 2005 - May 2008)