Understanding forced alignment errors in Hindi-English code-mixed speech - a feature analysis

Abstract

Forced alignment methods have recently seen great progress in the fields of acoustic-phonetics studies of low-resource languages. Code-mixed speech however, presents complex challenges to forced-alignment techniques, because of the longer phonemic inventory of bilingual speakers, the nature of accented speech, and the confounding interaction of two languages at a frame level. In this paper, we use the Montreal Forced Aligner to annotate the Phonetically Balanced Code- Mixed read-speech corpus (7.4 hours; 113 speakers) in 3 different training environments (code-mixed, Hindi and English). Additionally, we present an analysis of alignment errors using phonological and data-driven features using Random Forest and Linear mixed effects models. We find that contextual influence of neighbouring phonemes influences the error in alignment most significantly, when compared against any other features. Many of the alignment errors by phonological features can be explained by their acoustic distinctiveness. Additionally, the amount of training data by phone type also contributed to lowering their respective error rates.