Goodness of Pronunciation Pipelines for OOV Problem

TL;DR

This paper presents pipelines for Goodness of Pronunciation that address the OOV problem at testing time by expanding vocabularies and removing unknown phonemes, improving pronunciation scoring accuracy.

Contribution

It introduces three novel pipelines—Online, Offline, and Hybrid—for OOV handling in GoP computation, integrating lexicon expansion and phoneme posterior analysis.

Findings

Effective removal of UNK and SPN phonemes improves scoring accuracy

Hybrid pipeline combines advantages of online and offline methods

Utilities provided facilitate future research in pronunciation assessment

Abstract

In the following report we propose pipelines for Goodness of Pronunciation (GoP) computation solving OOV problem at testing time using Vocab/Lexicon expansion techniques. The pipeline uses different components of ASR system to quantify accent and automatically evaluate them as scores. We use the posteriors of an ASR model trained on native English speech, along with the phone level boundaries to obtain phone level pronunciation scores. We used this as a baseline pipeline and implemented methods to remove UNK and SPN phonemes in the GoP output by building three pipelines. The Online, Offline and Hybrid pipeline which returns the scores but also can prevent unknown words in the final output. The Online method is based per utterance, Offline method pre-incorporates a set of OOV words for a given data set and the Hybrid method combines the above two ideas to expand the lexicon as well work per utterance. We further provide utilities such as the Phoneme to posterior mappings, GoP scores of each utterance as a vector, and Word boundaries used in the GoP pipeline for use in future research.