Detection and Analysis of T/D Deletion in Librispeech

Abstract

In this study we developed a new method for automatic identification of t/d deletion. Our method achieved 94% accuracy on TIMIT and 87% on human-annotated data from Librispeech. We then conducted an analysis of t/d deletion on more than 500k tokens in Librispeech. The following results were found: (1) /d/ is more likely to be deleted than /t/; (2) t/d is more likely to be deleted when preceded by a nasal or a coronal obstruent; (3) In terms of the following phone, the rate of t/d deletion from low to high was: vowels and pause <; glides and liquids <; other phones; (4) In terms of the morphological class, the rate of t/d deletion from high to low was: stem > semi-weak past tense > regular past tense; (5) t/d is less likely to be deleted when the phonological neighborhood density (PND) is higher.