A Transfer Learning Approach for Pronunciation ScoringMarvelo Sancinetti, Jazmin Vidal, Cynthia Bonomi and Luciana Ferrer

Departamento de Computación, FCEyN, Universidad de Buenos Aires (UBA), Argentina
CONICET-UBA, Instituto de Investigación en Ciencias de la Computación (ICC), Argentina



DOI. (https://doi.org/10.48550/arXiv.2111.00976)

Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators. Standard systems generate a score for each phone in a phrase using models trained for automatic speech recognition (ASR) with native data only. Better performance has been shown when using systems that are trained specifically for the task using non-native data. Yet, such systems face the challenge that datasets labelled for this task are scarce and usually small. In this paper, we present a transfer learning-based approach that leverages a model trained for ASR, adapting it for the task of pronunciation scoring. We analyze the effect of several design choices and compare the performance with a state-of-the-art goodness of pronunciation (GOP) system. Our final system is 20% better than the GOP system on EpaDB, a database for pronunciation scoring research, for a cost function that prioritizes low rates of unnecessary corrections. 




Read the PDF

Partagez :