• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.4
• /
• pp.501-506
• /
• 2008

Statistical POS tagging is prone to error, because of the inherent limitations of statistical data, especially single source of data. Therefore it is widely agreed that the possibility of further enhancement lies in exploiting various knowledge sources. However these data sources are bound to be inconsistent to each other. This paper shows the possibility of using maximum entropy model to Korean language POS tagging. We use as the knowledge sources n-gram data and trigger pair data. We show how perplexity measure varies when two knowledge sources are combined using maximum entropy method. The experiment used a trigram model which produced 94.9% accuracy using Hidden Markov Model, and showed increase to 95.6% when combined with trigger pair data using Maximum Entropy method. This clearly shows possibility of further enhancement when various knowledge sources are developed and combined using ME method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.235-244
• /
• 2004

We propose a format of a binary phrase structure grammar with composite labels. The grammar adopts binary rules so that the dependency between two sub-trees can be represented in the label of the tree. The label of a tree is composed of two attributes, each of which is extracted from each sub-tree so that it can represent the compositional information of the tree. The composite label is generated from part-of-speech tags using an automatic labeling algorithm. Since the proposed rule description scheme is binary and uses only part-of-speech information, it can readily be used in dependency grammar and be applied to other languages as well. In the best-1 context-free cross validation on 31,080 tree-tagged corpus, the labeled precision is 79.30%, which outperforms phrase structure grammar and dependency grammar by 5% and by 4%, respectively. It shows that the proposed rule description scheme is effective for parsing Korean.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1809-1815
• /
• 2003

This paper presents a human friendly system using fuzzy inference as a Part of study to embody intelligent ship. We also build intelligent ship's steering system to take advantage of speech recognition that is a part of the human friendly interface. It can bring an effect such as labor decrement in ship. In order to design the voice instruction based ship's steering gear control system, we build of the voice instruction based learning(VIBL) system based on speech recognition and intelligent learning method at first. Next, we design an quartermaster's operation model by fuzzy inference and construct PC based remote control system. Finally, we applied the unposed control system to the miniature ship and verified its effectiveness.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.6
• /
• pp.539-545
• /
• 2011

This paper describes an intelligent service robot system for managing a store in an unmanned environment. The robot can be a good replacement for humans because it is possible to work all day and to remember lots of information. We design a system architecture for configuring many intelligent functions of intelligent service robot system which consists of four layers; a User Interaction Layer, a Behavior Scheduling Layer, a Intelligent Module Layer, and a Hardware Layer. We develop an intelligent service robot 'Part Timer' based on the designed system architecture. The 'Part Timer' has many intelligent function modules such as face detection-recognition-tracking module, speech recognition module, navigation module, manipulator module, appliance control module, etc. The 'Part Timer' is possible to answer the phone and this function gives convenient interface to users.

• Proceedings of the KSPS conference
• /
• 2000.07a
• /
• pp.47-58
• /
• 2000

For the learners of English as a foreign language, oral repetition of model sentences is an e essential practice to improve their listening and speaking abilities of English. Skill training of both speech perception and production is involved in this practice. This paper reports on an observation of production e$\pi$ors in such practice made by Japanese college students in my class. The teaching material used is intended for acquainting the learners with basic English rhythm and intonation p patterns. The students were required to repeat each sentence in a series of conversations after a model reading. Although the vocabulary and expressions were rather limited, I monitored different kinds of errors in their repetition. Putting aside intonation, their difficulties are classified into five types; 1. Omission of words or morphemes, 2. Addition of unnecessary words or morphemes, 3. Replacement of words, 4. Japanization of English sounds, 5. Wrong rhythm caused by improper stress assignment. Accurate listening, especially to weakly stressed syllables and to assimilated sounds, as has often been pointed out, is the most difficult part in perception for them. Japanese sound system interferes in production of English sounds. More often than not their knowledge of grammar or the context does not work at all to guess the words they are hearing

• MALSORI
• /
• no.25_26
• /
• pp.52-64
• /
• 1993

This paper aims to explore the rhythmic phenomena of standard Korean by an experimental phonetic method. A total of 16 informants taking part in this experiment were divided into four groups : old males(OM) and old females(OF) in their fifties and young males(YM) and young females(YF) in their twenties. The informants were asked to read speech data consisting of two rhythmic units, each of which began with a stressed syllable with a long wowel. Starting with the frame / 'ma:1 'ma:nta /, the first rhythmic unit was expanded up to five syllables in all while keeping the second rhythmic unit constant with a view to investigate the pattern of increase in the interstress time interval. The results of this study are as follows: 1. There is a considerable difference between yen and old generations with respect to the duration of interstress interval . The young generation tends to speak faster than the old generation. This observation is supported by difference in the interstress intervals as exhibited by OM(389.66), OF(473), YM(275.55), YF(285.83) in the test frame '말 많다' ['ma:1 'ma:nta]. 2. Young and old generations showed a different tendency in the increase rate of duration between mono-syllables and polysyllables. In other words, the rhythm of young generation shows the tendency of syllable-timed language whereas that of old generation clearly leans towards the stressed-timed language.

• Speech Sciences
• /
• v.12 no.4
• /
• pp.141-152
• /
• 2005

This paper shows the tonal patterns of English conjunctive utterances produced by Korean speakers of English, presenting that Korean speakers realize either the H - phrase tone or the H% boundary tone at the phrase-final part of the conjunctive utterances. Based on Pierrehumbert & Hirschberg's (1990) claim that either H- or H% tone indicates that a phrase is related to the following one, Korean speakers seem to produce the satisfactory patterns of edge tones in conjunctive sentences. In the experiment, we made up conjunctive sentences including both coordinate conjunctions such as and, but, or, and so and subordinate conjunctions like if, when and though. We varied the stimuli according to the existence of a comma and the lengths of connecting words and phrases. We also divided the subjects into two levels of English proficiency based on their English written test scores to see if Korean speakers' performance ability of edge tones is related with their general competence of English. Results show that Korean speakers produced 84% of the H- phrase tone in intermediate phrases and H-L% and L-H% boundary tones in intonational phrases. Also, coordinate and subordinate conjunctions show little difference in their tonal contours, and the existence of a comma or the lengths of connecting words and phrases do not affect Korean speakers' production of the H- phrasal tone and the H% boundary tone. This may suggest that pitch accents, rather than edge tones, should be put more focus on in teaching English intonation in Korea as much work has already shown that Korean speakers have serious problem with producing pitch accents in speaking English.

• MALSORI
• /
• no.35_36
• /
• pp.1-12
• /
• 1998

This study aims to investigate the prosodic characteristics of Korean discourse sentences, especially focusing the initial and final part of a sentence. 50 disourse sentences were read in two different styles; one, sentence by sentence, the other, continuous of all 50's. First, we tried to get two kinds of ratios from the acoustic results: first, ratio of the final syllable to the initial syllable in first word in a sentence; second, ratio of the final syllable to the initial syllable in last word in a sentence. We, then, calculated statistical values of the ratios including mean, standard deviation, minimum, maximum, and p-values in t-test. With respect to duration, there were little difference between two different styles. If any, we could see tiny unharmonious durational aspect in the initial of continuous reading. More concisely, there could be observed some deviation from standard. In case of F0, there was prominent statistical difference between ratios of last words in two styles. This difference might play a role as a prosodic feature. Energy seems to show similar pattern with that of F0. The results showed that final syllable in last word was pronounced with about 85 % of initial syllable in the same context and the last words in continuous speech were strongly articulated compared with those of sentence by sentence reading.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.57-64
• /
• 2018

The purpose of the present study was to explore the radiological and acoustic characteristics of "Arae-a" (/${\cdot}$/) articulation in two male Jeju language speakers, focusing on selected measures in radiological images derived from computed tomography scans, as well as the first and the second formant measures in selected vowels. An elderly male speaker (a 78-year-old) and a young male speaker (a 34-year-old) participated in the study. During the production of four selected vowels, the shape of the vocal tract was identified, and selected measures were obtained from the elderly participant's computed tomography (CT) scans. For acoustic analysis, the participants were given a list of near-minimal pairs consisting of 112 words and asked to read them aloud. The results indicated that the "Arae-a" (/${\cdot}$/) articulation of the elderly speaker showed unique acoustic and radiological characteristics compared to other similar vowels, thus presenting substantial consistency with the descriptions of the "Hunminjeongeum Haeryebon." In contrast, the F1 and F2 measures of the young male's /${\cdot}$/ articulation were not distinguished from those of /ㅗ/. Current results, in part, support the scientific principles underlying the invention of "Arae-a," which reflects the shape of the vocal tract during production, and the necessity for further research.

• Speech Sciences
• /
• v.11 no.3
• /
• pp.7-21
• /
• 2004

The present study aims to investigate domain-initial strengthening phenomenon, which refers to strengthening of articulatory gestures at the initial positions of prosodic domains. More specifically, this paper presents the result of an experimental study of initial syllables with onset consonants (initial-syllable vowels henceforth) of various prosodic domains in English and Hamkyeong Korean, a pitch accent dialect spoken in the northern part of North Korea. The durations of initial-syllable vowels are compared to those of second vowels in real-word tokens for both languages, controlling both stress and segmental environment. Hamkyeong Korean, like English, tuned out to strengthen the domain-initial consonants. With regard to vowel durations, no significant prosodic effect was found in English. On the other hand, Hamkyeong Korean showed significant differences between the durations of initial and non-initial vowels in the higher prosodic domains. The theoretical implications of the findings are as follows: The potentially universal phenomenon of initial strengthening is shown to be subject to language specific variations in its implementation. More importantly, the distinct phonetics- phonology model (Pierrehumbert & Beckman, 1998; Keating, 1990; Cohn, 1993) is better equipped to account for the facts in the present study.