I am a senior algorithm engineer at Vind.
Past
- AI/ML tech lead at Consigli.
- Machine learning scientist (VP) within the Machine Learning Center of Excellence at J.P. Morgan Chase.
- PhD student at CSTR where I worked on automatic speech recognition with Steve Renals and Peter Bell
- Interned at Bloomberg
- Interned at Sonos in the Advanced Technology team, supervised by Daniele Giacobello
- Collected the Self-dialogue Corpus as part of team Edina in the Amazon Alexa Prize
- Built a sound shredder for the CitySounds project
- Helped build a Norwegian speech synthesis voice for Cereproc
- TA for Automatic Speech Recognition and Machine Learning Practical
- Theatre consultant for Charcoalblue, advising on audiovisual and acoustics design
- Software tester and mechanic for the stage technology company Visual act
- MSc Artificial Intelligence, University of Edinburgh
- BMus Music & Sound Recording (Tonmeister), IoSR, University of Surrey
- Various modules: calculus, linear algebra, electromagnetism and psychology, University of Oslo
Publications
- P. Bell, J. Fainberg, O. Klejch, J. Li, S. Renals, P. Swietojanski, “Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview” [IEEE, ArXiv, GitHub], IEEE Open Journal of Signal Processing 2020
- J. Fainberg, O. Klejch, E. Loweimi, P. Bell, S. Renals, “Acoustic model adaptation from raw waveforms with SincNet” [Code], ASRU 2019
- O. Klejch, J. Fainberg, P. Bell, S. Renals, “Speaker adaptive training using model agnostic meta-learning” [Code], ASRU 2019
- J. Fainberg, O. Klejch, S. Renals, P. Bell, “Lattice-based lightly-supervised acoustic model training” [Code], Interspeech 2019
- O. Klejch, J. Fainberg, P. Bell, S. Renals, “Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models”, arXiv:1906.11521, 2019
- J. Fainberg, B. Krause, M. Dobre, M. Damonte, E. Kahembwe, D. Duma, B. Webber, F. Fancellu, “Talking to myself: self-dialogues as data for conversational agents” [Data], arXiv:1809.06641, 2018
- E. Klein, S. Chapple, J. Fainberg, C. Magill, M. Parker, C. Raab, J. Silvertown, “Capturing the sounds of an urban greenspace”, Smart Data and Smart Cities 2018
- O. Klejch, J. Fainberg, P. Bell, “Learning to adapt: a meta-learning approach for speaker adaptation” [Code], Interspeech 2018
- B. Krause, M. Damonte, M. Dobre, D. Duma, J. Fainberg, F. Fancellu, E. Kahembwe, J. Cheng, B. Webber, “Edina: Building an Open Domain Socialbot with Self-dialogues” [Data] , Proc. Alexa Prize 2017
- J. Fainberg, S. Renals, P. Bell, “Factorised representations for neural network adaptation to diverse acoustic environments”, Interspeech 2017
- P. Bell, J. Fainberg, C. Lai, M. Sinclair, “A system for real time collaborative transcription correction”, Interspeech 2017
- J. Fainberg, P. Bell, M. Lincoln and S. Renals, “Improving children’s speech recognition through out-of-domain data augmentation”, Interspeech 2016
Patents
- S. Moran, A. Emami, F. Silavong, J. Fainberg, A. Tiwari, A. Georgiadis, B. Moriarty, S.O. Adebayo, G. Papadopoulos, R. Saphal, R.F. Keith, R. Otter, S. Hall, “Detecting Secrets in Source Code”, 2023
- N. D’Amato, D. Giacobello, J. Fainberg, K. Hartung, “Multiple Stage Network Microphone Device with Reduced Power Consumption and Processing Load”, 2020
- J. Fainberg, D. Giacobello, K. Hartung, “Systems and Methods for Selective Wake Word Detection Using Neural Networks Models”, 2020
Theses
- “Robust learning of acoustic representations from diverse speech data”, PhD thesis, University of Edinburgh, 2020
- “Improving Children’s Speech Recognition through Out of Domain Data Augmentation”, MSc thesis, University of Edinburgh, 2015
- “Sound Source Separation in Reverberant Environments using Interaural Coherence in a Probabilistic Model of Localisation”, BMus thesis (Poster), University of Surrey, 2014