• Korean Journal of Cognitive Science
• /
• v.24 no.4
• /
• pp.301-321
• /
• 2013

For the task of sentence ordering, this paper attempts to utilize the Entity-Grid model, a type of entity-based modeling approach, as well as Latent Semantic analysis, which is based on vector space modeling, The task is well known as one of the fundamental tools used to measure text coherence and to enhance text generation processes. For the implementation of the Entity-Grid model, we attempt to use the syntactic roles of the nouns in the Korean text for the ordering task, and measure its impact on the result, since its contribution has been discussed in previous research. Contrary to the case of German, it shows a positive result. In order to obtain the information on the syntactic roles, we use a strategy of using Korean case-markers for the nouns. As a result, it is revealed that the cues can be helpful to measure text coherence. In addition, we compare the results with the ones of the LSA-based model, discussing the advantages and disadvantages of the models, and options for future studies.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.55-66
• /
• 2021

Proper prosody in reading allows the reader to naturally convey the meaning, which manifests as changes in pitch, loudness, and speech rate. Children with reading disability face difficulty in delivering information due to poor prosody. This study identified the difference in prosodic features between children with reading disabilities and nondisabled children through means of reading tasks. Reading tasks, according to sentence types (short sentences, assumptions/conditions, intentions, relative-clause), were recorded by 15 children studying in the 3rd to 6th grade in elementary school. Children with reading disability had a statistically significant wider range of pitch, slower speech rate, more frequent usage of pauses, longer total pause duration, and steeper pitch slope than nondisabled one in sentence-final and -medial words. Children with reading disability, therefore, exhibited a less natural and expressive reading than nondisabled children. Through this study, the characteristics of prosody observed in children with reading disability were identified and the need for an approach for effective intervention was also suggested.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.381-388
• /
• 2020

This paper discusses English Hedges or Hedging Expressions on the basis of their morphosyntactic-pragramatic properties within the perspective of sociolinguistics. The term, 'Hedges' for the past decades since Lakoff(1973), has received little attention from the English grammar circles such as morphosyntax and the generative grammar theories. This paper presents a more comprehensive approach to the identification, distributions, functions, and the morphosyntactic properties of English Hedges. The earlier research on English Hedges in the 70's show that hedges are metalinguistic or mitadiscourse expressions which constitute a means for executing Politeness strategy in pragmatics. Nonetheless, research from the interface of syntactic-pragmatics has been scarce. This article suggests a more complex body of English hedges that have not been extensively discussed in the literature. Additionally, their configurational domain is to be proposed as part of the PolP with [±hedged] above CP⁺ (or CP beyond). The ramifications of the current study are suggested in terms of comparative linguistics, EFL/ESL studies of English for global communication, and pragmatics-sensitive machine translation studies in the forseeable future.

• Cross-Cultural Studies
• /
• v.46
• /
• pp.297-325
• /
• 2017

In this paper, I would like to reconsider the evidential category (or the mediation category) in languages with language specific values, especially in Korean and French evidentials. We tried to analyze how the evidentials are represented in both languages including their linguistic markers (grammatical, lexical or discursive) and their semantic meanings. According to the precedent studies from the general linguistic point of view, we would like to reconsider the semantic meanings of both languages' grammatical markers, the so-called Korean retrospective marker '-te-' and French conditionals in the framework of the enunciative operation theory suggested by $Descl{\acute{e}}s$ & $Guentch{\acute{e}}va$ (2000), which proposed to classify the type of discourse by the language-independent description tools conceived after the enunciation theory suggested by Bally (1965), Benveniste (1956), Culioli (1973). Through this approach, we would like to contribute to establishing the linguistic basis not only for the general linguistic research to determine the invariant meaning of linguistic evidentials and their system, but also for the applied linguistics to the language engineering field.

• Phonetics and Speech Sciences
• /
• v.16 no.2
• /
• pp.99-109
• /
• 2024

Coarticulation is affected by the continuous movement of the articulator within a limited time and space through the neighboring segments and various overlaps. This study investigated the differences in coarticulation characteristics of children with reading disabilities and nondisabled children in CVC and VCV syllables consisted of stops, affricates, and vowels (a, i, u). The subjects were 13 children with reading disabilities and nondisabled children in the 2nd to 6th grades in elementary school. Two second formants were measured. One was measured at the point where the vowel began, and the other was measured at the mid point of the vowel stable section. Regression analysis was performed with F2 onset and F2 of the following vowel to obtain the locus equation (LE). 3-way ANOVA was conducted to the slope of the LE according to the groups (reading disabilities vs. nondisabled), places of articulation, and phonation types. In CVC syllable, dyslexic children showed a flatter slope than nondisabled children. With respect to the places of articulation, velar or bilabial sounds showed steeper LE slope than alveolar or palatal sounds. There were no main effects regarding group and phonation types variable for VCV syllable, and the significant differences in the places of articulation were also differed from the results for the CVC syllables. This study confirmed that dyslexic children showed a different pattern of coarticulation slope depending on the syllable structure. We also found that the higher pause rate of the dyslexic children had a stronger effect on the coarticulation in VCV structures.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.79-86
• /
• 2024

Transformer models have shown remarkable performance in extracting meaningful information from sequential input data such as text and images, and are gaining attention as end-to-end models for speech recognition. This study compared the performances of the Transformer speech recognition model and its enhanced versions, the Conformer and E-Branchformer, when applied to Korean speech recognition. Using Korean speech data from AIHub, we prepared a training set of approximately 7,500 hours and evaluated the models using the ESPnet toolkit. Additionally, we compared syllables and subwords as recognition units and analyzed the performance differences with changes in the number of tokens using Byte Pair Encoding. The results showed that the E-Branchformer achieved the best performance in Korean speech recognition and Conformer outperformed Transformer but degraded in performance for long utterances owing to cross-attention alignment errors. We aimed to determine the optimal settings by analyzing the performance changes with subword token adjustments. This study comprehensively evaluated model accuracy and processing speed to maximize the efficiency of Korean speech recognition. This is expected to contribute to the training of large-scale Korean speech recognition models and improve Conformer recognition errors. Future research should include additional experiments with diverse Korean speech datasets and enhance the recognition performance through structural improvements in the Conformer.