8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

An Evaluation of a Spoken Document Retrieval Baseline System in Finish

Mikko Kurimo (1), Ville Turunen (1), Inger Ekman (2)

(1) Helsinki University of Technology, Finland
(2) University of Tampere, Finland

This paper presents a baseline spoken document retrieval system in Finnish. Due to its agglutinative structure, Finnish speech can not be adequately transcribed using the standard large vocabulary continuous speech recognition approaches. The definition of a sufficient lexicon and the training of the statistical language models are difficult, because the words appear transformed by many inflections and compounds. In this work we apply a recently developed unlimited vocabulary speech recognition system that allows the use of n-gram language models based on morpheme-like subword units discovered in an unsupervised manner. In addition to word-based indexing, we also propose an indexing based on the subword units provided directly by our speech recognizer. In an initial evaluation of newsreading in Finnish, we obtained a fairly low recognition error rate and average document retrieval precisions close to that from human reference transcripts.

Full Paper

Bibliographic reference.  Kurimo, Mikko / Turunen, Ville / Ekman, Inger (2004): "An evaluation of a spoken document retrieval baseline system in finish", In INTERSPEECH-2004, 1585-1588.