Am\'elioration des Performances des Syst\`emes Automatiques de Reconnaissance de la Parole pour la Parole Non Native

TL;DR

This paper introduces two novel methods to adapt automatic speech recognition systems for non-native speakers, significantly reducing error rates by modeling phoneme confusions and leveraging graphemic constraints.

Contribution

It presents new adaptation techniques combining phoneme confusion modeling and graphemic constraints to improve non-native speech recognition accuracy.

Findings

22.5% relative reduction in sentence error rate

34.5% relative reduction in word error rate

Effective adaptation for non-native accents

Abstract

In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models through integration of acoustic models from the mother tong. The phonemes of the target language are pronounced in a similar manner to the native language of speakers. We propose to combine the models of confused phonemes so that the ASR system could recognize both concurrent pronounciations. The second method we propose is a refinment of the pronounciation error detection through the introduction of graphemic constraints. Indeed, non native speakers may rely on the writing of words in their uttering. Thus, the pronounctiation errors might depend on the characters composing the words. The average error rate reduction that we observed is (22.5%) relative for the sentence error rate, and 34.5% (relative) in word error rate.