The success of supervised deep neural networks (DNNs) in speech recognition cannot be
transferred to zero-resource languages where the requisite transcriptions are unavailable …

Recently, the debate about what kind of speech data is most appropriate for linguistic
research has intensified. Generally, with 'laboratory speech'defenders on the one hand and …

This paper describes the development of the Korean corpus of spontaneous speech, also
called the Seoul corpus. The corpus contains the audio recording of the interview-style …

This article presents two studies investigating how the situation in which speech is uttered
affects the frequency with which words are reduced. Study 1 is based on the Spoken Dutch …

Speech segmentation refers to the problem of determining the phoneme boundaries from an
acoustic recording of an utterance together with its orthographic transcription. This paper …

Abstract Words produced to infants exhibit phonetic modifications relative to speech to adult
interlocutors, such as longer, more canonical segments and prosodic enhancement …

Talkers differ greatly in the acoustic realization of speech sounds, a source of signal
variation that must be overcome by human and machine listeners. The present study …

This dissertation provides a new model of the phonology-morphology interface, focusing on
Phonologically Conditioned Allomorphy (PCA). In this model, UR selection occurs during the …

The phonetic reduction of words is a frequent phenomenon in spontaneous speech: many
words are realized with fewer or lenited segments when compared to their citation forms (eg …

Phonological theories differ as to whether phonological knowledge is abstract (eg,
phonemic), concrete (eg, exemplar-based), or some combination of the two. The …