In this paper, we present some recent improvements in our automatic speech segmentation system, which only needs the speech signal and the phonetic sequence of each sentence of a corpus to be trained. It estimates a GMM by using all the sentences of the training subcorpus, where each Gaussian distribution represents an acoustic class, which probability densities are combined with a set of condi...

An automatic transcription system has been developed to label and segment phonetic constituents of spontaneous American English without benefit of a word-level transcript. Instead, special-purpose neural networks classify each 10-ms frame of speech in terms of articulatory-acoustic-based phonetic features and the feature clusters are subsequently mapped to phonetic-segment labels using multilay...

Abstract Phonetic learner corpora represent a special type of spoken by providing detailed phonetic and phonological annotation in the form transcription as well segmentation labelling speech signal on levels segments, syllables, words sentences. This time-consuming post-processing enables better acoustic analysis data provides many options for using audio teaching foreign languages. It also of...

Although evidence is now available from several domains of language acquisition research that bilingual (BFLA) children differentiate their languages from the time of their earliest productions, studies in the phonetics-phonology domain have been sparse until recently. In this paper we first highlight some methodological issues that impact phonetic phonological data collection and interpretatio...

In this article, we present a summary of recent research linking speech perception in infancy to later language development, as well as a new empirical study examining that linkage. Infant phonetic discrimination is initially language universal, but a decline in phonetic discrimination occurs for nonnative phonemes by the end of the 1st year. Exploiting this transition in phonetic perception be...

In this paper we investigate an alternative approach to the design of low-bit rate (LBR) quantisation. This approach incorporates phonetic information into the structure of Line Spectral Frequency (LSF) codebooks. In prior work vector quantisation (VQ) has been used to quantise stochastic processes. Speech signals can, however, be described in terms of phonetic segments and linguistic rules. A ...

1. I will be arguing from data on vowel shifts in progress, and from principles of language change, that language specific phonetic implementation rules must be part of speaker knowledge, and thus part of language acquisition. Then, I will sketch an abstract model of what phonetic implementation could be like. Having argued these points, I will address how this approach interacts with phonologi...

There is an increasing need for automatic procedures to generate and validate phonetic transcriptions. As the production of manual phonetic transcriptions tends to be time-consuming, error-prone and costly, procedures have been developed to derive phonetic transcriptions automatically by means of automatic speech recogni­ tion technology. Such automatic phonetic transcrip­ tions are usually val...

Previous studies have shown that the adult speakers experience difficulty in discriminating nonnative phonetic contrasts that are not phonemic in their native language. The present study examined the internal structure of phonetic category representations in adults to seek an explanation for the impact of language experience on phonetic perception. Experiment 1 shows that language experience af...

Perception studies have long argued that phonetic confusions are more likely to happen across some phonetic features than other (e.g., place of articulation rather than manner) [1]. Similarly, we and others have noted that pronunciation variation occurs more frequently in unstressed syllables, and in syllable codas. This suggests that a phonetic information structure is at play, where for decod...