EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Designing Very Compact Decision Trees for Grapheme-to-Phoneme Transcription

Anne K. Kienappel (1), Reinhard Kneser (2)

(1) Philips Research Laboratories, Germany
(2) Philips Speech Processing, Germany

Decision trees are a popular technique for automatic generation of a phonetic transcription for a given word spelling. We investigate different methods of decision tree design to obtain more compact trees and at the same time better grapheme-to-phoneme transcription quality. We evaluate different approaches to decision tree question selection and pruning using one English and two German grapheme-to-phoneme transcription tasks. In particular, we present a method of automatic generation of decision tree questions from the training data that significantly improves decision tree design.

Full Paper

Bibliographic reference.  Kienappel, Anne K. / Kneser, Reinhard (2001): "Designing very compact decision trees for grapheme-to-phoneme transcription", In EUROSPEECH-2001, 1911-1914.