Tom Bäckström

Associate Professor
Associate Professor
T412 Department of Information and Communications Engineering

My research is focused on ethically sustainable speech communications technology, which refers to methods that use resources efficiently and ecologically and which do not expose the privacy or security of user more than necessary. I am the initiator and first chair of the ISCA Special Interest Group "Security and Privacy in Speech Communication". Previously, I have contributed to several international standards such as 3GPP Enhanced Voice Services and MPEG Unified Speech and Audio Coding. My current research topics include privacy-preserving speech processing, disentangled representations of speech, perception and design of privacy and trust, as well as modelling of speech interaction.

Full researcher profile
https://research.aalto.fi/...
Telefonnummer
+358504066120

Kompetensområde

speech processing, speech coding, security and privacy in speech communication, speech enhancement, 111 Mathematics, 112 Statistics and probability, 113 Computer and information sciences, 213 Electronic, automation and communications engineering, electronics, Signal processing, Information systems science, Software engineering, operating systems, man-computer interaction, Communications engineering

Utmärkelser

Outstanding Reviewer Award

This certifies that Tom Bäckström was one of the Top 2% of Reviewers for INTERSPEECH 2023.
Award or honor granted for a specific work Speech Interaction Technology Aug 2023

Forskningsgrupp

  • Speech Interaction Technology

Publikationer

Optimizing the Performance of Text Classification Models by Improving the Isotropy of the Embeddings using a Joint Loss Function

Joseph Attieh, Abraham Zewoudie, Vladimir Vlassov, Adrian Flanagan, Tom Bäckström 2023 Document Analysis and Recognition – ICDAR 2023 - 17th International Conference, Proceedings

Privacy in Speech Technology

Tom Bäckström 2023 Proceedings of the IEEE

Low-complexity Real-time Neural Network for Blind Bandwidth Extension of Wideband Speech

Esteban Gómez Mellado, Mohammadhassan Vali, Tom Bäckström 2023 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings

Privacy and Quality Improvements in Open Offices Using Multi-Device Speech Enhancement

Silas Rech, Mohammadhassan Vali, Tom Bäckström 2023 3rd Symposium on Security and Privacy in Speech Communication

The Internet of Sounds: Convergent Trends, Insights and Future Directions

Luca Turchet, Mathieu Lagrange, Cristina Rottondi, György Fazekas, Nils Peters, Jan Østergaard, Frederic Font, Tom Bäckström, Carlo Fischione 2023 IEEE Internet of Things Journal

Interpretable Latent Space Using Space-Filling Curves for Phonetic Analysis in Voice Conversion

Mohammadhassan Vali, Tom Bäckström 2023 Proceedings of Interspeech Conference

Stochastic Optimization of Vector Quantization Methods in Application to Speech and Image Processing

Mohammadhassan Vali, Tom Bäckström 2023 International Conference on Acoustics, Speech, and Signal Processing

Speech Localization at Low Bitrates in Wireless Acoustics Sensor Networks

Mariem Bouafif, Pablo Perez Zarazaga, Tom Bäckström, Zied Lachiri 2022 Frontiers in Signal Processing

Introduction to Speech Processing

Tom Bäckström, Okko Räsänen, Abraham Zewoudie, Pablo Perez Zarazaga, Liisa Koivusalo, Sneha Das, Esteban Gómez Mellado, Mariem Bouafif, Daniel Ramos 2022

NSVQ: Noise Substitution in Vector Quantization for Machine Learning

Mohammadhassan Vali, Tom Bäckström 2022 IEEE Access