This work presents experiments on four segmental training algorithms for mixture density HMMs. The segmental versions of SOM and LVQ3 suggested by the author are compared against the conventional segmental K-means and the segmental GPD. The recognition task used as a test bench is the speaker dependent, but vocabulary independent automatic speech recognition. The output density function of each...

Several approaches to Chinese dialect identification based on segmental and prosodic features of speech are described in this paper. When using segmental information only, the system performs phonotactic analysis after speech utterances have been tokenized into sequences of broad phonetic classes. The second scheme comprises prosodic models which are trained to capture tone sequence information...

This paper describes the results of a study of the phonetic and phonological factors affecting the rhythm and timing of spoken Korean. Stepwise construction of a CART model was used to uncover the contribution and relative importance of phrasal, syllabic, and segmental contexts. The model was trained from a corpus of 671 read sentences, yielding 42,000 segments each annotated with 69 linguistic...

In various priming paradigms, segmental overlap (i.e. phonological or orthographical overlap) between the target and prime word has been demonstrated to facilitate picture naming. But features extending over several segments are rarely controlled for in stimulus selection. Some attention has been paid to such suprasegmental features, but inconsistent findings have been obtained. The presented s...

The Cambrian fossil record of euarthropods (extant arachnids, myriapods, crustaceans, hexapods) has played a major role in understanding the origins of these successful animals and indicates that early ancestors underwent an evolutionary transition from soft-bodied taxa (lobopodians) to more familiar sclerotized forms with jointed appendages [1-3]. Recent advances in paleoneurology and developm...

Uniparental disomy of chromosome 14 (UPD(14)) results in one of two distinct abnormal phenotypes depending upon the parent of origin. The discordance between the maternal and paternal UPD(14) phenotypes may result from overexpression and/or underexpression of one or more imprinted genes located on chromosome 14q. A cluster of imprinted genes has been identified and localised to 14q32. However, ...

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous CRF-based acoustic models, it does not rely on an external system to provide features or segmentation boundaries. Instead, this model marginalises out all t...

A top-down hierarchical system based on deep neural networks is investigated for the modeling of prosody in speech synthesis. Suprasegmental features are processed separately from segmental features and a compact distributed representation of highlevel units is learned at syllable-level. The suprasegmental representation is then integrated into a frame-level network. Objective measures show tha...

There are 10 major dialects in China. Most people in dialectal regions are bilingual speakers, i.e. native dialect and Mandarin. Although lots of people can speak Mandarin, they speak it with different accents (called regional accented Chinese in this paper) depending on how well they grasp the language. In this study, we categorize the regional accented Chinese into 3 levels of accents accordi...

The paper considers the task of recognizing environmental sounds, which plays a critical role in human’s perception of an auditory context in audiovisual materials. A variety of features have been proposed for audio recognition, either frame-based or segmental. Here, we propose a two-stage framework to combine modeling in these two levels. First, the Gaussian Mixture Models(GMMs) are built base...