• 말소리와 음성과학
• /
• 제14권4호
• /
• pp.11-17
• /
• 2022

This study investigates closure durations of Korean stops in terms of laryngeal contrasts, places of articulation, and three positions within words. Twenty-two Korean speakers produced the nonsense words containing Korean stops found in word-initial and word-final positions and between vowels. The statistical results showed that the closure durations differed significantly by laryngeal contrast and place of articulation. In addition, the differences by position within words were marginally significant. The closure durations were in the order of lenis < aspirated < fortis stops by laryngeal contrast, velar < alveolar < bilabial stops by place of articulation, and word-final < word-initial < between vowels by positions within words. The laryngeal contrasts were neutralized in word-final position as per coda neutralization in Korean phonology. This study shows that closure durations should be considered a valuable phonetic cue to identify stops on par with voice onset time and f0.

• 음성과학
• /
• 제15권2호
• /
• pp.21-30
• /
• 2008

The current study investigated distributional properties of the Korean Accentual Phrase and their implication to word segmentation. The properties examined were the frequency of various AP tonal patterns, the types of tonal patterns that are imposed upon content words, and the average number and temporal location of content words within the AP. A total of 414 sentences from the Read speech corpus and the Radio corpus were used for the data analysis. The results showed that the 84% of the APs contained one content word, and that almost 90% of the content words are located in AP-initial position. When the AP-initial onset was not an aspirated or tense consonant, the most common AP patterns were LH, LHH, and LHLH (78%), and 88% of the multisyllabic content words start with a rising tone in AP-initial position. When the AP-initial onset was an aspirated or tense consonant, the most common AP patterns were HH, HHLH, and HHL (72%), and 74% of the multisyllabic content words start with a level H tone in AP-initial position. The data further showed that 84.1% of APs end with the final H tone. The findings provide valuable information about the prosodic pattern and structure of Korean APs, and account for the results of a previous study which showed that Korean listeners are sensitive to AP-initial rising and AP-final high tones (Kim, 2007). This is in line with other cross-linguistic research which has revealed the correlation between prosodic probability and speech processing strategy.

• 말소리와 음성과학
• /
• 제8권1호
• /
• pp.19-24
• /
• 2016

The Korean high back vowels /o/ and /u/ have been reported to be in a state of near-merger especially among young female speakers. Along with cross-generational changes, the vowel position within a word has been reported to render different phonetic realization. The current study examines native English speakers' ability to attend to the phonetic cues that distinguish the two merging vowels and the positional effects (word-initial vs. word-final) on the identification accuracy. 28 two-syllable words containing /o/ or /u/ in either initial or final position were produced by native female Korean speakers. The CV part of each target word were excised and presented to six native English speakers. The results showed that although the identification accuracy was the lowest for /o/ in word- final position (41%), it increased up to 80% in word-initial position. The acoustic analyses of the target vowels showed that /o/ and /u/ were differentiated on the height dimension only in word-initial position, suggesting that English speakers may have perceived the distinctive F1 difference retained in the prominent position.

• ETRI Journal
• /
• 제38권4호
• /
• pp.703-713
• /
• 2016

In this paper, we present a segmentation-based method for offline Farsi handwritten word recognition. Although most segmentation-based systems suffer from segmentation errors within the first stages of recognition, using the inherent features of the Farsi writing script, we have segmented the words into sub-words. Instead of using a single complex classifier with many (N) output classes, we have created N simple recurrent neural network classifiers, each having only true/false outputs with the ability to recognize sub-words. Through the extraction of the number of sub-words in each word, and labeling the position of each sub-word (beginning/middle/end), many of the sub-word classifiers can be pruned, and a few remaining sub-word classifiers can be evaluated during the sub-word recognition stage. The candidate sub-words are then joined together and the closest word from the lexicon is chosen. The proposed method was evaluated using the Iranshahr database, which consists of 17,000 samples of Iranian handwritten city names. The results show the high recognition accuracy of the proposed method.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.1284-1284
• /
• 2024

Leveraging large language models and safety accident report data has unique potential for analyzing construction accidents, including the classification of accident types, injured parts, and work processes, using unstructured free text accident scenarios. We previously proposed a novel approach that harnesses the power of fine-tuned Generative Pre-trained Transformer to classify 6 types of construction accidents (caught-in-between, cuts, falls, struck-by, trips, and other) with an accuracy of 82.33%. Furthermore, we proposed a novel methodology, saliency visualization, to discern which words are deemed important by black box models within a sentence associated with construction accidents. It helps understand how individual words in an input sentence affect the final output and seeks to make the model's prediction accuracy more understandable and interpretable for users. This involves deliberately altering the position of words within a sentence to reveal their specific roles in shaping the overall output. However, the validation of saliency visualization results remains insufficient and needs further analysis. In this context, this study aims to qualitatively validate the effectiveness of saliency visualization methods. In the exploration of saliency visualization, the elements with the highest importance scores were qualitatively validated against the construction accident risk factors (e.g., "the 4m pipe," "ear," "to extract staircase") emerging from Construction Safety Management's Integrated Information data scenarios provided by the Ministry of Land, Infrastructure, and Transport, Republic of Korea. Additionally, construction accident precursors (e.g., "grinding," "pipe," "slippery floor") identified from existing literature, which are early indicators or warning signs of potential accidents, were compared with the words with the highest importance scores of saliency visualization. We observed that the words from the saliency visualization are included in the pre-identified accident precursors and risk factors. This study highlights how employing saliency visualization enhances the interpretability of models based on large language processing, providing valuable insights into the underlying causes driving accident predictions.

• 한국정보시스템학회지:정보시스템연구
• /
• 제19권1호
• /
• pp.1-17
• /
• 2010

This paper proposes an updating policy of indoor moving object databases (IMODB) for location-based services. our method applies the Ka1man filter on the recently collected measured positions to estimate the moving object's position and velocity at the moment of the most recent measurement, and extrapolate the current position with the estimated position and velocity. If the distance between the extrapolated current position and the measured current position is within the threshold, in other words if they are close then we skip updating the IMODB. When the IMODB needs to know the moving object's position at a certain moment T, it applies the Kalman filter on the series of the measurements received before T and extrapolates the position at T with the estimations obtained by the Kalman filter. In order to verify the efficiency of our updating method, we performed the experiments of applying our method on the series of measured positions obtained by applying the fingerprinting indoor positioning method while we are actually walking through the test bed. In the analysis of the test results, we estimated the communication saving rate of our method and the error increment rate caused by the communication saving.

• 말소리와 음성과학
• /
• 제9권4호
• /
• pp.69-76
• /
• 2017

The current study investigated the productions of /ɨ/ and /${\Lambda}$/ in Kyungsang Korean, which is known for undergoing a dispersion for the younger generation. Specifically, to identify the nature of /ɨ/ and /${\Lambda}$/ in Kyungsang Korean, this study examined the linguistic and social factors affecting directions and degrees of the /ɨ/-/${\Lambda}$/ dispersion. Sixteen young speakers of Kyungsang Korean repeated 112 (near) minimal pairs containing the two target vowels. The formant values of each production as well as the Euclidean distance between the two vowels were analyzed for four manipulated factors: gender (male vs. female), the existence of carrier phrases (words in isolation vs. words with a carrier phrase), the lexical status of stimulus words (real-word pairs vs. nonsense-word pairs), and the vowel position within a word (word-initial positions vs. word-final positions). The results indicated that the female speakers produced the two target vowels more distinctively than the male speakers, and so did when the words were produced in isolation. The results also revealed that the Euclidean distances were greater for the real-word pairs and in word-initial positions. Overall, the results suggested that the Kyungsang Korean speakers in their 20s could distinctively produce the two vowels /ɨ/ and /${\Lambda}$/, but this vowel dispersion is not a completed process, but an ongoing one.

• 인문언어
• /
• 제6권
• /
• pp.147-166
• /
• 2004

Whitehead's discussion of language is not to be found in any one book or article. It is interwoven with his discussion of many other questions. He was, however, greatly concerned with the problem of symbolism in general and the uses of language. He regards language, spoken or written, as an instrument devised by men to aid them in their adjustment to the environment in which they live Language is used for many specific purposes in the process of this adjustment. Words are employed not only to refer to data and to express emotions. They may be used also to record experiences, and thoughts about these experiences. Worts also function as instruments in the organization of experiences as they are considered in retrospect. Thus words free us from the bondage of the immediate. And Whitehead's theory of meaning is implicit in his discussion of the functions of language. According to him, the human mind is functioning symbolically when some components of its experience elicit consciousness, beliefs, emotions, and usages, respecting other components of its experiences. The former set of components are the 'symbols', and the latter set constitute the 'meaning' of the symbols. Whitehead points out that one word may have several meanings, i.e. refer to several different data. In order to understand, thus, the meaning to which a word refers, it is sometimes very important to appreciate the system of thought within which a person is operating. Further, Whitehead's discussion of language includes a number of cogent warning the deficiencies of language, and hence the need for great care in the use of words. In fact, language developed gradually. For the most part we have created words designed to deal with practical problems. Attention focuses on the prominent features in a situation, in particular the changing aspects of things. With reference to such data our words are relatively adequate. However, this issues in an unfortunate superficiality. The enduring, the subtle, the complex and the general aspects of the universe do not have adequate verbal representation. for this reason, Whitehead's position concerning the uses of language in speculative philosophy is stated with pungent directness. The uncritical trust in the adequacy of language is one of the main errors to which philosophy is liable. Since ordinary language does not do justice to the generalities, profundities and complexities of life, it is obvious that philosophy requires new words and phrases, or at least the revision of familiar words and phrases. Proceeding to develop the theme Whitehead contends that words and phrases must be stretched towards a generality foreign to their ordinary usage. In the same vein Whitehead refers to the need to realize that language which is the tool of philosophy needs to be redesigned just as in physical science available physical apparatus needs to be redesigned. But even these words and phrases, stretched or redesigned, are never completely adequate in philosophical speculations. They are, in his opinion, merely a great improvement over ordinary language or the language science, mathematics or symbolic logic.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권3호
• /
• pp.199-208
• /
• 2022

Inertial Navigation System (INS)/Global Navigation Satellite System (GNSS) integrated navigation system can be used for land vehicle navigation. When the GNSS signal is blocked in a dense urban area or tunnel, however, the problem of increasing the error over time is unavoidable because navigation must be performed only with the INS. In this paper, Non-Holonomic Constraints (NHC) information is utilized to solve this problem. The NHC may correct some of the errors of the INS. However, it should be noted that NHC information is not applicable to all areas within the vehicle. In other words, the lever arm effect occurs according to the distance between the Inertial Measurement Unit (IMU) mounting position and the NHC effective point, which causes the NHC condition not to be satisfied at the IMU mounting position. In this paper, an INS/GNSS/NHC integrated navigation filter is designed, and this filter has a function to compensate for the lever arm effect. Therefore, NHC information can be safely used regardless of the vehicle's driving environment. The performance of the proposed technology is verified through Monte-Carlo simulation, and the performance is confirmed through experimental test.

• 한국컴퓨터정보학회논문지
• /
• 제18권1호
• /
• pp.55-62
• /
• 2013

본 논문은 어린이나 노약자, 손이 불편한 장애우 등이 컴퓨터의 타자 실력을 증가시키기 위한 타자게임을 설계 구현하였다. 이 게임의 구성은 화면에 임의의 단어가 나타나는 한글이나 영문의 단어를 정해진 시간 안에 올바르게 치면 점수가 증가되고, 틀리게 치게 되면 점수가 감점되며, 올바르게 입력을 하면 앞서가는 벌레나 곤충을 잡을 수 있도록 따라가는 방식으로 되어 있다. 틀린 단어를 입력하면 앞서가는 벌레와 거리가 더 멀어지게 되며, 정해진 시간 안에 많은 단어의 입력을 하여 올바른 입력을 하면 앞서가는 벌레와 충돌되어 벌레를 없앨 수 있는 기능을 제공한다. 이는 두되 계발을 촉진시키면서 키보드의 단어 입력과 같은 타자 실력을 증가시키기 위함이다. 흥미를 유발하면서도 타자 실력과 키보드의 글자의 위치를 암기할 수 있는 장점이 있으며 정서적으로도 도움이 될 것으로 기대된다.