Skip to content

Okko Räsänen

  • Doctor of Science (technology)
  • Aalto University School of Electrical Engineering
  • 10h-indexImpact measure calculated using publication and citation counts. Updated daily.
  • 351CitationsNumber of citations received by Okko's publications. Updated daily.

Other IDs

Research interests

Language AcquisitionSpeech TechnologyCognitive Science

About

I'm interested in computational self-learning systems that can sense their environment through a number of sensors and build meaningful representations of the sensory data in the absence of human supervision. I'm especially interested in the question how human infants learn their language by simply interacting with their environment. In addition to speech processing, my interests include the development of statistical learning and data analytics tools for all types of complex sensory data, also in case of multiple parallel data streams. As an example, I have experience with processing of audio-, EEG-, accelerometer-, and magnetic field signals. I have also experience with the prediction of electricity production, transfer, and consumption data. Currently, I'm doing research and managing our projects "From Data to Intelligence" (D2I) SHOK project funded by Tekes and "Computational Modeling of Language Acquisition" funded by the Academy of Finland. Specialties: speech processing, sensory data analytics, machine learning, cognitive science

Co-authors (37)

  • Cumhur Erkut

Publications (5)

  • Making predictable unpredictable with style – Behavioral and electrophysiological evidence for the critical role of prosodic expectations in the perception of prominence in speech

    • Kakouros S
    • Salminen N
    • Räsänen O
    N/AReaders
    0Citations
    Get full text
  • Pre-linguistic segmentation of speech into syllable-like units

    • Räsänen O
    • Doyle G
    • Frank M
    N/AReaders
    0Citations
    Get full text
  • Comparison of non-parametric Bayesian Mixture Models for syllable clustering and zero-resource speech processing

    • Seshadri S
    • Remes U
    • Räsänen O
    N/AReaders
    1Citations
    Get full text
  • Evaluation of spectral tilt measures for sentence prominence under different noise conditions

    • Kakouros S
    • Rasanen O
    • Alku P
    N/AReaders
    1Citations
    Get full text
  • Speaking style conversion from normal to Lombard speech using a glottal vocoder and Bayesian GMMs

    • Lopez A
    • Seshadri S
    • Juvela L
    • et al.
    N/AReaders
    0Citations
    Get full text

Education

Aalto-yliopisto Sahkotekniikan korkeakoulu