Acoustic word embeddings are typically created by training a pooling fun...
Self-supervised speech representations are known to encode both speaker ...
Parsing spoken dialogue presents challenges that parsing text does not,
...
Given the strong results of self-supervised models on various tasks, the...
While corpora of child speech and child-directed speech (CDS) have enabl...
Word segmentation, the problem of finding word boundaries in speech, is ...
Parsing spoken dialogue poses unique difficulties, including disfluencie...
Research in sociology and linguistics shows that people use language not...
Prior work has shown that Twitter users use skin-toned emoji as an act o...
Non-native speakers show difficulties with spoken word processing. Many
...
We present LemMED, a character-level encoder-decoder for contextual
morp...
In the first year of life, infants' speech perception becomes attuned to...
Acoustic word embeddings are fixed-dimensional representations of
variab...
Can artificial neural networks learn to represent inflectional morpholog...
Prosody is a rich information source in natural language, serving as a m...
Recent studies have introduced methods for learning acoustic word embedd...
Acoustic word embeddings are fixed-dimensional representations of
variab...
Previous work has shown that for low-resource source languages, automati...
Given a large amount of unannotated speech in a language with few resour...
The cognitive mechanisms needed to account for the English past tense ha...
Lemmatization aims to reduce the sparse data problem by relating the
inf...
Unsupervised subword modeling aims to learn low-level representations of...
We present a simple approach to improve direct speech-to-text translatio...
We highlight several issues in the evaluation of historical text
normali...
Speech-to-text translation has many potential applications for low-resou...
How can we effectively develop speech technology for languages where no
...
Unsupervised segmentation and clustering of unlabelled speech are core
p...
We explore the problem of translating speech to text in low-resource
sce...
Zero-resource speech technology is a growing research area that aims to
...
In settings where only unlabelled speech data is available, speech techn...