Department of Signal Processing and Acoustics

Speech Interaction Technology

Our objective is to improve spoken interaction, in applications such as telecommunication as well as when using speech interfaces. We develop methods which are efficient and sustainable with respect to resources, provide high sound quality and intuitive interaction while simultaneously retaining the privacy of users. A particular area of interest are environments where multiple people interact with multiple devices, which requires advanced methods for communication, authentication and processing.
Group Members

Research Overview

We currently specialize in the following research areas:

  • Speech and audio coding, distributed coding and acoustic sensor networks
  • Security and privacy in speech communication
  • Acoustic authentication methods
  • Speaker recognition

Teaching

Our department provides the following courses on speech and language technology: 

We are part of the major in Machine Learning, Data Science and Artificial Intelligence (Macadamia) in the Master's Programme in Computer, Communication and Information Sciences.

Team Photos

Group members

Sneha Das

Doctoral candidate

Latest publications

Can you identify me from a crowd?

Tom Bäckström 2019

Super-Wideband Spectral Envelope Modeling for Speech Coding

Guillaume Fuchs, Chamran Ashour, Tom Bäckström 2019 Proceedings of Interspeech

Sound Privacy: A Conversational Speech Corpus for Quantifying the Experience of Privacy

Pablo Perez Zarazaga, Sneha Das, Tom Bäckström, V. V. Vidyadhara Raju, Anil Vuppala 2019 Interspeech

Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling

Pablo Perez Zarazaga, Tom Bäckström, Stephan Sigg 2019 European Signal Processing Conference

Concept for encoding of information

Tom Bäckström, Christian Fischer Pedersen, Johannes Fischer, Matthias Huettenberger, Alfonso Pino 2019

Vocoding techniques

Tom Bäckström 2019 Sage Encyclopedia of human communication sciences and disorders

Overlap-add Windows with Maximum Energy Concentration for Speech and Audio Processing

T. Bäckström 2019 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019; Brighton; United Kingdom; 12-17 May 2019 : Proceedings

Paradoxes in Standardization

Tom Bäckström 2019

Optimizing MFCC Settings for Low-Complexity VAD Systems - a Case Study

Alexandra Craciun, Tom Bäckström 2018 ITG-Fb. 282: Speech Communication
More information on our research in the Research database.
  • Published:
  • Updated:
Share
URL copied!