• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.1
• /
• pp.20-28
• /
• 1992

Co-articulation is one of major factors that make connected word recognition difficult. This Study Considers the fact that the head Part Of the following word is changed by the Preceding word in a connection point, by applying the co-articulation model, and adj usting the following word .We choose a critical damping second order linear system for the co-articulation model, combining a one-stage DP matching recognition algorithm with this model, and Investigating the effects. The recognition experiment is carried out for 35 Korean 4 connected digits spoken by 5 male speakers, and recognition rate Is upgraded by 4.7 percent.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.57-62
• /
• 2003

Using EPG, the stop and fricative portions of the Korean and English afficates were examined to find out whether the stop and fricative portions of Korean affricates are the same as those of English ones in articulation, as generally assumed in the literature. The English affricate in the word 'choose' is classified as alveopalatal just like the Korean affricate in the word 'cam'. The results of the EPG data showed that Korean affricates were not articulated the same as those in English, especially in the stop portion. In English, the stop portion of 'choose' was quite similar to /t/ as 'tooth', but in Korean, the stop portion of 'cam' was somewhat different from /t/ in 'tam'. More specifically, the stop portion of /t/ in 'tam' was articulated with the contact at the upper teeth and the alveolar ridge, but the stop portion of /t/ in 'cam' was articulated with the contact in the alveopalatal region. This shifting in the place of articulation of the stop portions of the Korean affricate (from dental and alveolar to alveopalatal) can be explained. Unlike English affricates, the stop portions of Korean affricates and the fricative portions of Korean affricates are co-articulated at the same place of articulation.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.3
• /
• pp.421-435
• /
• 2017

Recently, due to the saturation of ground structures and the overpopulation of pipeline facilities requires to development of underground structures as an alternative to ground structures. Thus, mechanized tunnel construction of the shield TBM method has been increasing in order to prevent vibration and noise problems in construction of the NATM tunnel for the urban infrastructure construction. Tunnel construction plan for the tunnel line should be formed in a sharp curve to avoid building foundation and underground structures and it is inevitable to develop a shield TBM technology that suits the sharp curve tunnel construction. Therefore, this study is about the structural stability technology of the articulation jack, shield jack and skin plate for the shield TBM thrust in case of the mechanized tunnel construction that is a straight and sharp curve line. The construction case study and shield TBM operation principle are examined and analyzed by the theoretical approach. The torque of the cutter head, the thrust of the articulation jack and the shield jack, the amount of over cutting for curve is important respectively in shield TBM construction of straight and sharp curve line. In addition, it is very important to secure the stability of the skin plate structure to ensure the safety of the inside worker. This study examines the general structure and construction of the equipment, experimental simulation was carried out through numerical analysis to examine the main factors and structural stability of the skin plate structure. The structural stability of the skin plate was evaluated and optimizes the shape by comparing the loads of the articulation jack by selecting the virtual soil to be applied in a straight and sharp curve line construction. Since the present structure and operation method of the shield TBM type in domestic constructions are very similar, this study will help to develop the localized shield TBM technology for the new equipment and the vulnerability and stability review.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.49-59
• /
• 2020

In this paper, we propose a speech animation synthesis specialized in Korean through a rule-based co-articulation model. Speech animation has been widely used in the cultural industry, such as movies, animations, and games that require natural and realistic motion. Because the technique for audio driven speech animation has been mainly developed for English, however, the animation results for domestic content are often visually very unnatural. For example, dubbing of a voice actor is played with no mouth motion at all or with an unsynchronized looping of simple mouth shapes at best. Although there are language-independent speech animation models, which are not specialized in Korean, they are yet to ensure the quality to be utilized in a domestic content production. Therefore, we propose a natural speech animation synthesis method that reflects the linguistic characteristics of Korean driven by an input audio and text. Reflecting the features that vowels mostly determine the mouth shape in Korean, a coarticulation model separating lips and the tongue has been defined to solve the previous problem of lip distortion and occasional missing of some phoneme characteristics. Our model also reflects the differences in prosodic features for improved dynamics in speech animation. Through user studies, we verify that the proposed model can synthesize natural speech animation.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.9 no.1
• /
• pp.7-16
• /
• 1972

By analyzing the frequency of the speech under test to be affected the effect of a co-articulation, we find out the fact that a conversational speech is far from the collective sound continued by a monotone, and define also the frequency range of a Formant at the Korean conversational speech.

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.17-26
• /
• 2014

The present study examined epenthetic vowels produced by Korean learners of English in read sentences, in terms of acoustic measures and extra-phonological factors. The results demonstrated three main findings. First, epenthetic vowels had relatively high F1 values and a wide range of F2 values. Most of the epenthetic vowels were inserted near Korean high central vowels, but some vowels were inserted near front vowels due to co-articulation with surrounding vowels. Second, vowel epenthesis was affected by the context. The results showed that the epenthesis was frequently seen with word junctions between obstruents (e.g., stops-fricatives). Third, Korean learners were not affected by English background and were very weakly affected by orthography. English experience, which is one of the extra-phonological factors, was not related to epenthesis production. However, orthography, the other extra-phonological factor, very weakly affected the amount of epenthesis production. Nine percent of all epenthesis production was affected by the English past-tense suffix '-ed'; approximately 70% of the participants were affected by this suffix. The findings of the present study contributed to understanding vowel epenthesis. First, the study revealed that the epenthetic vowels produced by Korean learners of English were close to the high central vowel, supporting previous studies that the epenthetic vowel is quite close to the shortest vowel. Second, the study examined the various phonetic environments of epenthetic vowels, revealing that vowel epenthesis occurred more frequently in a certain phonetic circumstance.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.11
• /
• pp.63-75
• /
• 1998

Since many co-articulation problems are occurring in continuous spoken Korean language, several researches use words as a basic recognition unit. Though the word unit can solve this problem, it requires much memory and has difficulty fitting an input speech in a word list. In this paper, we propose an hidden Markov model(HMM) based recognition model that is an interconnection network of word HMMs for a syntax of sentences. To match suitably the input sentence into the continuous word list in the network, we use a level building search algorithm. This system represents the large sentence set with a relatively small memory and also has good extensibility. The experimental result of an airplane reservation system shows that it is proper method for a practical recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.401-406
• /
• 2002

Each Korean digit is composed of only a syllable, so recognizers as well as Korean often have difficulty in recognizing it. When digit strings are pronounced, the original pronunciation of each digit is largely changed due to the co-articulation effect. In addition to these problems, the distortion caused by various channels and noises degrades the recognition performance of Korean connected digit string. This paper dealt with some techniques to improve recognition performance of it, which include defining a set of PLUs by considering phonemic variations in Korean digit and constructing a recognizer to handle speakers various speaking styles. In the speaker-independent connected digit recognition experiments using telephone speech, the proposed techniques with 1-Gaussian/state gave string accuracy of 83.2%, i. e., 7.2% error rate reduction relative to baseline system. With 11-Gaussians/state, we achieved the highest string accuracy of 91.8%, i. e., 4.7% error rate reduction.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.312-318
• /
• 2006

The conventional lip-synch system has a two-step process, speech segmentation and recognition. However, the difficulty of speech segmentation procedure and the inaccuracy of training data set due to the segmentation lead to a significant Performance degradation in the system. To cope with that, the connected vowel recognition method using Head-Body-Tail (HBT) model is proposed. The HBT model which is appropriate for handling relatively small sized vocabulary tasks reflects co-articulation effect efficiently. Moreover the 7 vowels are merged into 3 classes having similar lip shape while the system is optimized by employing a class dependent SCHMM structure. Additionally in both end sides of each word which has large variations, 8 components Gaussian mixture model is directly used to improve the ability of representation. Though the proposed method reveals similar performance with respect to the CHMM based on the HBT structure. the number of parameters is reduced by 33.92%. This reduction makes it a computationally efficient method enabling real time operation.