Speech Group

Our goal is to generally improve the speech recognition methodology with the help of the new algorithms developed in our laboratory. Speech recognition offers challenging benchmarking tasks for efficient algorithms that can process and learn to represent large quantities of data. In addition to improving the acoustical models of phonemes we aim at developing new learning statistical language models for difficult large vocabulary continuous speech recognition tasks. The relevant pilot applications in our group range from unlimited vocabulary continuous dictation in different languages to audio indexing and speech-to-speech translation.
Situated at the Adaptive Informatics Research Centre the research group belongs to the Multimodal Interfaces group. In language modeling, speech translation and video indexing we work closely together with the Adaptive Natural Language Processing, Computational Cognitive Systems, Content-Based Image and Information Retrieval research groups.

People

Mikko Kurimo	Kalle Palomäki	Janne Pylkkönen	Ville Turunen	Ulpu Remes	Heikki Kallasjoki	Reima Karhila	Teemu Ruokolainen	Andre Mansikkaniemi	Sami Keronen

New members (Master's students): Peter Smit, Lasse Hyyrynen

Ex-members (since 2000): Panu Somervuo, Simo Broman, Vesa Siivola, Antti Puurula, Teemu Hirsimäki, Matti Varjokallio

Speech projects

Some key references

Software: VariKN language modeling toolkit

Demos: WWW-interface to our Finnish recognizer

Contact: Mikko Kurimo, Mikko.Kurimo at hut.fi

Our unlimited vocabulary continuous speech recognizer processes audio data by generating and comparing hypotheses consisting of automatically optimized morph units.