Mária Gósy

Development of a Large Spontaneous Speech Database of Agglutinative Hungarian Language

In this paper, a large Hungarian spoken language database is introduced. This phonetically-based multi-purpose database contains various types of spontaneous and read speech from 333 monolingual speakers (about 50 minutes of speech sample per speaker). This study presents the background and motivation of the development of the BEA Hungarian database, describes its protocol and the transcription procedure, and also presents existing and proposed research using this database. Due to its recording protocol and the transcription it provides a challenging material for various comparisons of segmental structures of speech also across languages.

Changes in articulation accompanying functional changes in word usage

Two words in present-day Hungarian, the conjunction tehat ‘that is’ and ‘consequently’ and the pronoun ilyen ‘like this’ seem to be undergoing a functional change, acquiring the function of fillers, while retaining their former lexical function, too. Twenty narratives were drawn from the Hungarian Spontaneous Speech Corpus (BEA), to analyze the acoustic-phonetic patterns of these words. Both words showed significant differences in duration depending on function. The first and second formant values of the conjunction tehat showed significant differences depending on whether it was used as a filler or in its original function as a conjunction. The formants of the stressed vowel in the pronoun ilyen did not show any differences with either males or females, but the second formant of the unstressed vowel, depending on function, showed significant variations with male subjects. Apparently, females make an unconscious distinction between the two functions only by varying the time structure of the word. Our data confirmed that these words are indeed undergoing a functional change, which is manifested in changes of their temporal patterns and, to some extent, in the articulation of their vowels.

Alternative Organization of Speech Perception Deficits in Children.

Childrens first‐language perception base takes shape gradually from birth onwards. Empirical research has confirmed that children may continue to fall short of age‐based expectations in their speech perception. The purpose of this study was to assess the contribution of various perception processes in both reading and learning disabled children. A series of experiments was carried out with 450 Hungarian‐speaking schoolchildren: learning disabled, reading disabled and typically developing control first‐, second‐, and third‐graders. Data from seven perception tasks—focusing on acoustic, phonetic and phonological perception processes—were analysed. Results revealed that (i) there is no linear development in all groups across ages, (ii) correct performance is characteristic of both the perception process and the type of disability, and (iii) a specific pattern of organization can be drawn up as a factor in development.

On the Early History of Hungarian Speech Research

This article provides a critical review on the beginnings and the development of Hungarian speech research from the 1700s up to the modern era. The aim is to highlight the tradition in order to keep a good memory of the useful results of the past and of the Hungarian researchers who achieved them in this scientific field. Farkas Kempelen, the Hungarian nobleman and his work will be introduced first. The paper then deals with the early achievements of experimental investigations, the description of the devices used, and the further developments. Results that are unknown in the phonetic and speech technology literature will be discussed.

Phonetic analysis and automatic prediction of vowel duration in Hungarian spontaneous speech

A large number of phonetic and phonology research papers analyzed segmental durations focusing on factors and interactions that determine their durations. The results often play an important role in Language Technology applications, for example in TTS (text-to-speech synthesis), ASR (automatic speech recognition) and are widely used in infocommunication. Speech sound duration depends on various factors such as phonetic quality, phonological context, phonological position in the word or in the utterance, speech style, etc. The multifunction dependence of vowel duration is more complex in those languages where vowel length is a distinctive feature like in Hungarian. The main goal of the present research was to analyze the physical durations of pairs of vowels in spontaneous speech that exhibit a phonological length opposition. In addition, we intended to develop an algorithm for automatic classification of the short and long vowels occurring in spontaneous speech. On the basis of these findings we intended to predict automatically the vowel durations based on three different methods. The measured data confirmed our hypothesis that phonologically short vs. long vowels would significantly differ in their physical durations in spontaneous speech. The results of the automatic vowel length classification also supported this finding. The third aspect of our investigations was to use different supervised learning methods in order to predict vowel duration, based on different feature vectors consisting of characteristic and spectral features. The best result was yielded by the combined features and FFNN were used. The correlation between the target and the predicted vowel duration was 0.79 while RMSE was 25 ms. The results obtained support the complexity of features affecting vowel duration, on the one hand, and indicate the temporal complexity of segments in spontaneous speech, as has been reported for Lithuanian, Czech, Hindi, Telugu and Korean, on the other hand.

Dichotic listening and sentence repetition performance in children with reading difficulties

ABSTRACT Numerous investigations have identified weaknesses in speech processing and language skills in children with dyslexia; however, little is known about these abilities in children with reading difficulties (RD). The primary objective of this investigation was to determine the utility of auditory speech processing tasks in differentiating children with RD from those with typical reading skills. It was hypothesized that children, who perform below grade level in reading, would also show poorer performance on both dichotic listening and sentence repetition tasks because of the reciprocal influences of deficient auditory speech processing and language abilities. A total of 180 Hungarian-speaking, monolingual 8-, 9- and 10-year-old children, with and without RD, participated in dichotic listening and sentence repetition (modified by noise and morphosyntactic complexity) tasks. Performances were compared across ability groups, age and gender. Children with RD evidenced significantly poorer performance than controls on both tasks. Effects for age and gender were more noticeable in students with RD. Our findings support the notion that reading deficiencies are also associated with poor auditory speech processing and language abilities in cases where dyslexia is not diagnosed. We suggest that these tasks may be used as easy and fast screening tests in the identification of RD.

Speech processing in children with functional articulation disorders

Abstract This study explored auditory speech processing and comprehension abilities in 5–8-year-old monolingual Hungarian children with functional articulation disorders (FADs) and their typically developing peers. Our main hypothesis was that children with FAD would show co-existing auditory speech processing disorders, with different levels of these skills depending on the nature of the receptive processes. The tasks included (i) sentence and non-word repetitions, (ii) non-word discrimination and (iii) sentence and story comprehension. Results suggest that the auditory speech processing of children with FAD is underdeveloped compared with that of typically developing children, and largely varies across task types. In addition, there are differences between children with FAD and controls in all age groups from 5 to 8 years. Our results have several clinical implications.

Boundary Markers in Spontaneous Hungarian Speech

The aim of this paper is an objective presentation of temporal features of spontaneous Hungarian narratives, as well as a characterization of separable portions of spontaneous speech. Ten speakers’ spontaneous speech materials taken from the BEA Hungarian Spontaneous Speech Database were analyzed in terms of hierarchical units of narratives (durations, speakers’ rates of articulation, number of words produced, and the interrelationships of all these). We conclude that (i) the majority of speakers organize their narratives in similar temporal structures, (ii) thematic units can be identified in terms of certain prosodic criteria, (iii) there are statistically valid correlations between factors like the duration of phrases, the word count of phrases, the rate of articulation of phrases, and pausing characteristics, and (iv) these parameters exhibit extensive variability both across and within speakers.

Synthesized Speech for Evaluation of Children’s Hearing and Acoustic-Phonetic Perception

This paper describes the auditory screening function of low redundancy synthesized Hungarian words. They have successfully been applied to hearing screening of children. The same artificial words highlight the children’s speech perception disorders in the case of normal hearing. The basic hypothesis is applicable to many other languages as well.