• Proceedings of the KSPS conference
• /
• 1997.07a
• /
• pp.92-114
• /
• 1997

This study is aimed to grasp the actual problems of the perception of English rhythm and intonation structure by Korean University students who have studied English in the secondary schools for the past six years, and to establish the systems of English rhythm and intonation structure for the Korean students of English. For this study, the listening test is provided, and 100 students are chosen as the subjects of the study. The noticeable findings are summarized as follows: (1) Koreans perceive the words stress comparatively well in nonsense words, unfamiliar place names, and familiar word. (2) Koreans do not perceive the isochrony of English rhythm well enough. The perception of the sentence stress is very unstable, especially in the sentence involved in polysyllabic words, compound words, and 'emphatic stress' pr 'contrastive stress'(or in the different rhythmic patterns). (3) Koreans do not perceive the nucleus well enough. The perception of the nucleus is more stable in content words than in function words, at the end of a sentence than in the middle of a sentence, and in monosyllabic words than in the polysyllabic words. (4) Koreans do not perceive the boundary(or pause) of intonation group well enough. The perception of the pause is unstable in the long or complex sentence. (5) Koreans discriminate the meaning of English word stress comparatively well, especially in disyllabic words. But the discrimination is somewhat unstable in polysyllabic words and between 'adjective' and 'verb' (6) Koreans' discrimination of the intonation meaning is below the level. Koreans do not perceive the differences of intonation meaning according to the pitch accent or the focus. In conclusion, the writer will propose the procedures for the teaching of rhythm and intonation in the following order: word stress drill longrightarrowstressed and reduced syllables drilllongrightarrowrhythm group drilllongrightarrowthe varying rhythm drilllongrightarrowsentence stress drilllongrightarrownucleus drill longrightarrowintonation group drilllongrightarrowlong utterance drill of more than two intonation group.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1
• /
• pp.24-32
• /
• 1997

This study aims to describe, at one aspect, the relativity between syntactic structure and prosodic phrasing, and at the other, to establish a suitable phrasing pattern to produce more natural synthetic speech. To get meaningful results, all the word boundaries in the prosodic database were statistically analyzed, and assigned by the proper boundary type. The resulting 10 types of prosodic boundaries were classified into 3 types according to the strength of the breaks, which are zero, minor, and major break respectively. We have found out that the durational information was a main cue to determine the major prosodic boundary. Using the bigram and trigram of syntactic information, we predicted major and minor classification of boundary types. With brigram model, we obtained the correct major break prediction rates of 4.60%, 38.2%, the insertion error rates of 22.8%, 8.4% on each Test-I and Test-II text database respectively. With trigram mode, we also obtained the correct major break prediction rates of 58.3%, 42.8%, the insertion error rates of 30.8%, 42.8%, the insertion error rates of 30.8%, 11.8% on Test-I and Test-II text database respectively.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.23-27
• /
• 2003

Recently attempts to we the syllable as the recognition unit to enhance performance in continuous speech recognition hate been reported. However, syllables are worse in their trainability than phones and the former have a disadvantage in that contort-dependent modeling is difficult across the syllable boundary since the number of models is much larger for syllables than for phones. In this paper, we propose a method to enhance the trainability for the syllables in Korean and phoneme-context dependent syllable modeling across the syllable boundary. An experiment in which the proposed method is applied to word recognition shows average 46.23% error reduction in comparison with the common syllable modeling. The right phone dependent syllable model showed 16.7% error reduction compared with a triphone model.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.86-93
• /
• 2021

This paper aims to investigate a novel affix prevalently and productively used in social media, which is assumed to be borrowed from English into Korean loanblens. The novel affix is composed of a prefix-like and a suffix-like elements, but it seems to be distinguished from other regular combinations of a prefix and a suffix. In analyzing the affix, we attempt to highlight its peculiarities of the affix with empirical data. First, the seemingly borrowed affix does not behave like affixes found in the donor language (English) or the recipient language (Korean) from a linguistic point of view. Both languages have circumfixation rarely available in productive word-formation processes. Second, no regular assimilation rules of Korean apply to the affix boundary, which would otherwise be mandatory to such syllable contact contexts. Last but not least, the affix form has no correspondence to the donor language, and therefore it is claimed to be derived through secretion and taken as a case of pseudo-anglicisms.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.57-64
• /
• 1999

In this paper, we investigated the robust endpoint detection algorithm in noisy environment. A new feature parameter based on a discrete wavelet transform is proposed for word boundary detection of isolated utterances. The sum of standard deviation of wavelet coefficients in the third coarse and weighted first detailed scale is defined as a new feature parameter for endpoint detection. We then developed a new and robust endpoint detection algorithm using the feature found in the wavelet domain. For the performance evaluation, we evaluated the detection accuracy and the average recognition error rate due to endpoint detection in an HMM-based recognition system across several signal-to-noise ratios and noise conditions.

• Korean Journal of Cognitive Science
• /
• v.21 no.4
• /
• pp.481-503
• /
• 2010

In the present study, we examined global and local characteristics of eye movements while 17 Korean third-graders read a Korean story and an expository text. In story reading, children fixated for about 213ms at an eojeol(word cluster), made a forward saccade of about 3.6 characters to the next eojeol, and regressed backward at 30.8% on average. In expository text reading, children fixated for about 214ms at an eojeol, made a forward saccade of about 3.3 characters to the next eojeol, and regressed backward at 31% on average. In addition, the effects of eojeol length, word frequency and landing position were examined. The gaze duration in the long ejoels was longer than in the short eojeols. In a further analysis where the repeatedly used eojeols were excluded, the eojeol length effect appeared in the low-frequency words, but seemed to disappear in the high-frequency words. In terms of landing position, the eyes seemed to land near the center of an eojeol more frequently than on the boundaries. When the eyes landed at the boundary of an eojeol, the eyes tended to fixate the eojeol again.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.1-5
• /
• 2003

In this paper, we realized a system that converts the character images of the printed Korean alphabet (Hangul) to the editable text documents by using the black and white CCD camera, We were able to abstract the contours information of the character which is based on the structural character by using the boundary tracing technique that is strong to the noise on the character recognition. By using the contours information, we recognized the horizontal vowels and vertical vowels of the character image and classify the character into the six patterns. After that, the character is divided to the unit of the consonant and vowel. The vowels are recognized by using the maximum length projection. The separated consonants are recognized by comparing the inputted pattern with the standard pattern that has the phase information of the boundary line change. We realized a system that the recognized characters are inputted to the word editor with the editable KS Hangul completion type code.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2238-2245
• /
• 2000

In this papr, eatue parameters, extracted using Wavelet transform for Korean isolated worked speech, are sued for speech detection and recognition feature. As a result of the speech detection, it is shown that it produces more exact detection result than eh method of using energy and zero-crossing rate on speech boundary. Also, as a result of the method with which the feature parameter of MFCC, which is applied to he recognition, it is shown that the result is equal to the result of the feature parameter of MFCC using FFT in speech recognition. So, it has been verified the usefulness of feature parameters using Wavelet transform for speech analysis and recognition.