Finite-state super transducers for compact language resource representation in edge voice-AI

• Published in: Systems science & control engineering Vol. 10; no. 1; pp. 636 - 644
• Main Authors: Dobrišek, Simon, Golob, Žiga, Žganec Gros, Jerneja
• Format: Journal Article
• Language: English
• Published: Macclesfield Taylor & Francis 31.12.2022; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: automatic grapheme-to-phoneme conversion; Dictionaries; Engines; finite-state super transducers; Platforms; pronunciation dictionary; Representations; Speech processing; Speech synthesis; Transducers; Words (language)
• ISSN: 2164-2583; 2164-2583
• DOI: 10.1080/21642583.2022.2089930

Finite-state transducers have been proven to yield compact representations of pronunciation dictionaries used for grapheme-to-phoneme conversion in speech engines running on low-resource embedded platforms. However, for highly inflected languages even more efficient language resource reduction methods are needed. In the paper, we demonstrate that the size of finite-state transducers tends to decrease when the number of word forms in the modelled pronunciation dictionary reaches a certain threshold. Motivated by this finding, we propose and evaluate a new type of finite-state transducers, called 'finite-state super transducers', which allow for the representation of pronunciation dictionaries by a smaller number of states and transitions, thereby significantly reducing the size of the language resource representation in comparison to minimal deterministic final-state transducers by up to 25%. Further, we demonstrate that finite-state super transducers exhibit a generalization capability as they may accept and thereby phonetically transform even inflected word forms that had not been initially represented in the original pronunciation dictionary used for building the finite-state super transducer. This method is suitable for speech engines operating on platforms at the edge of an AI system with restricted memory capabilities and processing power, where efficient speech processing methods based on compact language resources must be implemented.