• #425978

    Essential networking events for publishers across Europe, Asia, Latin America, Africa, Middle East and North America. 

Mikko Kurimo

Mikko Kurimo

Associate Professor, Speech and Language Processing at Aalto University

Mikko Kurimo (born in 1967) received the M.Sc. degree in technical physics and the Licentiate and the Doctor of Technology degrees in computer science from Helsinki University of Technology, Espoo, Finland in 1992, 1994 and 1997, respectively. He leads a research group which focuses on new machine learning methods for speech recognition, retrieval, and translation.

The AaltoASR project, which is led by Professor Mikko Kurimo at Aalto University, focuses on the development of an Automatic Speech Recognition system that is able to transcribe spoken Finnish language with a very high accuracy rate. The system, which started as a relatively simple spoken-language recognizer in the 1980s that was at first capable of handling around 1000 Finnish words, is today a complex piece of software that can recognize and transcribe not only isolated words but also spontaneous speech. The AaltoASR system comprises of complex procedures that accurately transform audio signals into linguistically-modelled speech units on the basis of a complex network of probabilistic distributions, thus making the system easily adaptable to various domains and styles.

A demonstration of the AaltoASR tool is available on the website of the Aalto Department of Signal Processing and Acoustics. Furthermore, a demonstration video on YouTube showcases the tool in action as it simultaneously transcribes a broadcast video of Finnish news. The AaltoASR tool is open source, and the developer version can be found on the tool’s GitHub page, with instructions in English found here. AaltoASR is available for research use via the Language Bank. ASR systems built on top of AaltoASR tools are also being used by companies for subtitling TV broadcasts in Finland and Sweden.