Automatic detection of phoneme or word-like units is one of the core objectives in zero- resource speech processing. Recent attempts employ self-supervised training methods …
Before they even speak, infants become attuned to the sounds of the language (s) they hear, processing native phonetic contrasts more easily than nonnative ones. For example …
Sociophonetics focuses on the relationship between phonetic or phonological form on the one hand, and social and regional factors on the other, working across fields as diverse as …
L Van Staden, H Kamper - 2021 IEEE Spoken Language …, 2021 - ieeexplore.ieee.org
Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping …
RH Baayen, M Linke - A practical handbook of corpus linguistics, 2021 - Springer
In this chapter we introduce the Generalized Additive Model (GAM). GAMs enable the analyst to investigate non-linear functional relations between a response variable and one …
C DiCanio, J Benn… - Language and Speech, 2021 - journals.sagepub.com
Phrase-final position is cross-linguistically the locus of both processes of phonetic reduction and processes of phonetic enhancement. In tone languages, phrasal position is a …
This article uses formal and usage-based data and methods to argue for a hybrid model of English tensed auxiliary contraction combining lexical syntax with a dynamic exemplar …
J Leinonen, S Virpioja, M Kurimo - Proceedings of the 23rd Nordic …, 2021 - aclanthology.org
Forced alignment is an effective process to speed up linguistic research. However, most forced aligners are language-dependent, and under-resourced languages rarely have …
DE Eddington, EK Brown - American Speech: A Quarterly of …, 2021 - read.dukeupress.edu
This article examines the production and perception of/t/in five US states: Indiana, Mississippi, New Mexico, Utah, and Vermont. For the production study, 94 participants read …