Knowledge-light Letter-to-Sound Conversion for Swedish with FST and TBL

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding


This paper describes some exploratory attempts to apply a combination of finite state
transducers (FST) and transformation-based learning (TBL, Brill 1992) to the problem of
letter-to-sound (LTS) conversion for Swedish. Following Bouma (2000) for Dutch, we employ
FST for segmentation of the textual input into groups of letters and a first transcription stage;
we feed the output of this step into a TBL system. With this setup, we reach 96.2% correctly
transcribed segments with rather restricted means (a small set of hand-crafted rules for the
FST stage; a set of 12 templates and a training set of 30kw for the TBL stage).
Observing that quantity is the major error source and that compound morpheme
boundaries can be useful for inferring quantity, we exploratively add good precision-low
recall compound splitting based on graphotactic constraints. With this simple-minded
method, targeting only a subset of the compounds, performance improves to 96.9%.


Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • General Language Studies and Linguistics


  • LTS, Swedish, grapheme-to-phoneme conversion for Swedish, letter-to-sound conversion for Swedish
Original languageEnglish
Title of host publicationProceedings of Fonetik 2006
EditorsGilbert Ambrazaitis, Susanne Schötz
PublisherLund University
Publication statusPublished - 2006
Publication categoryResearch
EventFonetik 2006 - Hörsalen, SOL, Lunds Universitet, Helgonabacken 12, Lund, Sweden
Duration: 2006 Jun 72006 Jun 9


ConferenceFonetik 2006

Bibliographic note

The information about affiliations in this record was updated in December 2015. The record was previously connected to the following departments: Linguistics and Phonetics (015010003)

Total downloads

No data available