• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.35-44
• /
• 2000

In this paper, we propose a new trajectory model for characterizing segmental features and their interaction based upon a general framework of hidden Markov models. Each segment, a sequence of vectors, is represented by a trajectory of observed sequences. This trajectory is obtained by applying a new design matrix which includes transitional information on contiguous frames, and is characterized as a polynomial regression function. To apply the trajectory to the segmental HMM, the frame features are replaced with the trajectory of a given segment. We also propose the likelihood of a given segment and the estimation of trajectory parameters. The obervation probability of a given segment is represented as the relation between the segment likelihood and the estimation error of the trajectories. The estimation error of a trajectory is considered as the weight of the likelihood of a given segment in a state. This weight represents the probability of how well the corresponding trajectory characterize the segment. The proposed model can be regarded as a generalization of a conventional HMM and a parametric trajectory model. The experimental results are reported on the TIMIT corpus and performance is show to improve significantly over that of the conventional HMM.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.27 no.4
• /
• pp.372-380
• /
• 2005

Condylar process of mandible, has the specialized anatomic structure compared with any other body structure, acts directly in connection with mastication and speech and so on. In general, mandibular condyle fractures have been managed by two methods as open and closed reduction. But, there are no reasonable consensus about the proper management of this injury. This study was designed for analysis of the prognosis of two methods of treatment, open and closed reduction, with positional change of fractured condyle and complications within 6 months post-intermaxillary fixation period. We conducted a retrospective analysis of 154 patients whose unilateral mandibular condyle fractures were treated by open or closed reduction in our department. The horizontal, sagittal, and coronal change of the condyle was examined using modified Towne's and panoramic radiographs before intermaxillary fixation(IMF), immediately after IMF, and at 6 months after IMF. Patients, whose mandibular condyle fractures were treated by closed reduction, had significantly shorter ramus height on the side of injury(P<0.05). But, fractured condylar fragments were displaced insignificantly with aspect to sagittal and coronal plane(P>0.05). The level of the fracture influenced the ramus length and the degree of coronal change in the closed reduction group(P<0.05). There was no significant correlation among the level of the fracture, treatment methods and complications(P>0.05). From the results obtained in this study, fractured mandibular condyles, were treated by closed reduction, had a tendency that continuous condylar displacement was occurred with aspect to horozontal and coronal plane in treatment period including intermaxillary fixation. And then there was a correlation between the level of the fracture and the position change in close reduction group statistically. These result suggested that care must be taken in basing treatment decisions on the degree of displacement of the condyle and in treating the mandibular condyle fractures for a long time.

• The Journal of the Korean dental association
• /
• v.49 no.4
• /
• pp.219-226
• /
• 2011

Snoring and obstructive sleep apnea (OSA) are common sleep disordered breathing conditions. Habitual snoring is caused by a vibration of soft tissue of upper airway while breath in sleeping, and obstructive sleep apnea is caused by the repeated obstructions of airflow for a sleeping, specially airflow of pharynx. Researchers have shown that snoring is the most important symptom connected with the obstructive sleep apnea syndrome The treatment is directed toward improving the air flow by various surgical and nonsurgical methods. The current surgical procedures used are uvulopalatopharyngoplasty(UPPP), orthognathic surgery, nasal cavity surgery. Among the nonsurgical methods there are nasal continuous positive air pressure(CPAP), pharmacologic therapy. weight loss in obese patient, oral appliance(sleep splint). Sleep splint brings the mandible forward in order to increase upper airway volume and prevents total upper airway collapse during sleep. However, the precise mechanism of action is not yet completely understood, especially aerodynamic factor. The aim of this study evaluated the effect of conservative treatment of snoring and OSAS by sleep splint through measured aerodynamic change by an aerophone II. We measured a airflow, sound pressure level, duration, mean power from overall airflow by aerophone II mask. The results indicated that on a positive correlation between a decrease in maximum airflow rate and a decrease in maximum sound pressure level, on a negative correlation between a decrease in maximum airflow rate and a increase in duration.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.123-126
• /
• 2004

본 논문은 잡음환경 하에서의 효율적인 문맥의존 음향 모델 구성에 대한 기초연구로서 잡음환경 하에서의 유사 음소단위 수에 따른 연속 음성인식 성능을 비교, 평가한 결과에 대한 보고이다. 기존의 연구[1,2]로부터 연속음성 인식의 경우 문맥종속모델은 변이음을 고려한 39유사음소를 이용한 경우가 48유사음소를 이용하는 것보다 더 좋은 인식성능을 나타냄을 알 수 있었다. 이 연구 결과를 바탕으로 본 연구에서는 잡음환경에서도 효율적인 문맥 의존 음향모델을 구성하기 위한 기초 연구를 수행하였다. 다양한 잡음환경을 고려하기 위해 White, Pink, LAB 잡음을 신호 대 잡음비(Signal to Noise Ratio) 5dB, 10dB, 15dB 레벨로 음성에 부가한 후 각 유사음소단위 수에 따른 연속음성인식 실험을 수행하였다. 그 결과, 39유사음소를 이용한 경우가 48유사음소를 이용한 경우보다 clear 환경인 경우에 약 $7\%$와 $17\%$ 향상된 단어인식률과 문장 인식률을 얻을 수 있었으며, 각 잡음환경에서도 39유사음소를 이용한 경우가 48유사음소를 이용한 경우보다 평균 적으로 $17\%$와 $28\%$ 향상된 단어인식률과 문장인식률을 얻을 수 있어 39유사음소 단위가 한국어 연속음성인식에 더 적합하고 잡음환경에서도 유효함을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.274-284
• /
• 2002

Word segmentation errors occurring in text preprocessing often insert incorrect words into recognition vocabulary and cause poor language models for Korean large vocabulary continuous speech recognition. We propose an automatic word segmentation algorithm using Markov chains and syllable-based n-gram language models in order to correct word segmentation error in teat corpora. We assume that a sentence is generated from a Markov chain. Spaces and non-space characters are generated on self-transitions and other transitions of the Markov chain, respectively Then word segmentation of the sentence is obtained by finding the maximum likelihood path using syllable n-gram scores. In experimental results, the algorithm showed 91.58% word accuracy and 96.69% syllable accuracy for word segmentation of 254 sentence newspaper columns without any spaces. The algorithm improved the word accuracy from 91.00% to 96.27% for word segmentation correction at line breaks and yielded the decomposition accuracy of 96.22% for compound-noun decomposition.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3
• /
• pp.242-247
• /
• 2004

Conventional keyword spotting systems use the connected word recognition network consisted by keyword models and filler models in keyword spotting. This is why the system can not construct the language models of word appearance effectively for detecting keywords in large vocabulary continuous speech recognition system with large text data. In this paper to solve this problem, we propose a keyword spotting system using pseudo N-gram language model for detecting key-words and investigate the performance of the system upon the changes of the frequencies of appearances of both keywords and filler models. As the results, when the Unigram probability of keywords and filler models were set to 0.2, 0.8, the experimental results showed that CA (Correctly Accept for In-Vocabulary) and CR (Correctly Reject for Out-Of-Vocabulary) were 91.1% and 91.7% respectively, which means that our proposed system can get 14% of improved average CA-CR performance than conventional methods in ERR (Error Reduction Rate).

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.24 no.3
• /
• pp.164-169
• /
• 2013

Objectives : We assessed the availability of Aberrant Behavior Checklist (ABC) for the evaluation of the pharmacological effect in autistic disorder. Methods : A retrospective review of the medical records of 27 children with autistic disorder, who visited the department of child and adolescent psychiatry of Kyungpook National University Hospital, from October 2011 to February 2013, was conducted. After treatment with risperidone, changes in the severity and improvement of symptoms were measured using ABC at the baseline, 2nd visit and 3rd visit, respectively. Results : The mean daily dose of risperidone increased from $0.66{\pm}0.27mg$ (baseline, initial dose) to $1.02{\pm}0.50mg$, 2nd visit, and $1.19{\pm}0.50mg$, 3rd visit. According to ABC, irritability, lethargy, hyperactivity, and inappropriate speech subscale scores decreased significantly from the baseline to 2nd visit. Irritability and Hyperactivity subscale scores decreased significantly from the 2nd to 3rd visit. All subscales and total scores of ABC decreased significantly from the baseline to 3rd visit. Conclusion : The results of this study suggest that ABC can be used as an efficient tool to measure the symptoms of autistic disorder and to evaluate the medication effect on continuous treatment.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.197-199
• /
• 2000

연속음성인식을 수행하기 위해서는 발음사전과 언어모델이 필요하다. 이 둘 사이에는 디코딩 단위가 일치하여야 하므로 발음사전 구축시 디코딩 단위로 표제어 단위를 선정하며 표제어 사이의 음운변화 현상을 반영한 발음사전을 구축하여야 한다. 한국어에 부합하는 음운변화현상을 분석하여 학습용 자동 발음열을 생성하고, 이를 통하여 발음사전을 구축한다. 전처리 단계로 기호, 단위, 숫자 등 전처리 과정 및 형태소 분석 과정을 수행하며, 디코딩 단위인 의사 형태소 단위를 생성하기 위해 규칙을 이용한 태깅 과정을 거친다. 이를 통해 나온 결과를 발음열 생성기 입력으로 하며, 결과는 학습용 발음열 또는 발음사전 구성을 위한 형태로 출력한다. 표제어간 음운변화 현상이 반영된 상태의 표제어 단위이므로 실제 음운변화가 반영되지 않은 상태의 표제어와는 그 형태가 상이하다. 이는 연속 발음시 생기는 현상으로 실제 인식에는 이 음운변화 현상이 반영된 사전이 필요하게 된다. 생성된 발음사전의 효용성을 확인하기 위해 다음과 같은 실험을 통해 성능을 평가하였다. 음향학습을 위하여 PBS(Phonetically Balanced Sentence) 낭독체 17200문장을 녹음하고 그 전사파일을 사용하여 학습을 수행하였고, 발음사전의 평가를 위하여 이 중 각각 3100문장을 사용하여 다음과 같은 실험을 수행하였다. 형태소 태그정보를 이용하여 표제어간 음운변화 현상을 반영한 최적의 발음사전과 다중 발음사전, 언어학적 기준에 의한 수작업으로 생성한 표준 발음사전, 그리고 표제어간의 음운변화 현상을 고려하지 않고 독립된 단어로 생성한 발음사전과의 비교 실험을 수행하였다. 실험결과 표제어간 음운변화 현상을 반영하지 않은 경우 단어 인식률이 43.21%인 반면 표제어간 음운변화 현상을 반영한 1-Best 사전의 경우 48.99%, Multi 사전의 경우 50.19%로 인식률이 5~6%정도 향상되었음을 볼 수 있었고, 수작업에 의한 표준발음사전의 단어 인식률 45.90% 보다도 약 3~4% 좋은 성능을 보였다.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.417-428
• /
• 1996

In this paper, a database interface system with natural language dialogue is designed and implemented. The system is made up of language analysis, context processing, dialogue processing and DB processing unit. The method for classifying and processing an undefined word in language analysis is proposed. It reduces the dictionary size, which gives difficulties in DB Interface. And the current DB Interfaces dealt with an input utterance independently. But the system in this paper provides a user with the interface environment in which he or she can have a continuous conversation with the system and retrieve DB information. Thus in this paper, speech acts which include user's inattentions well as propositional contents are defined, and user action hierarchical model for library DB retrieval is constructed. And the system uses the defined knowledge to recognize-user's plan, effectively understanding and managing the ongoing dialogue. And the system is implemented in the domain of library database in order to prove the proposed methods in this paper.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.31 no.1
• /
• pp.13-18
• /
• 2020

Background and Objective The purpose of this study is to report the effect of voice therapy using the voice reinforcement method (VRM) in patients with vocal nodules. It is one of the holistic voice therapy methods for improving vocal mechanisms. VRM includes not only direct and indirect voice therapy, but also trial therapy and self-practice. Composed of four stages: vocal hygiene education, relaxation, reinforcement, and generalization. Materials and Methods The subjects were 13 patients who were diagnosed with vocal nodules. Acoustic analysis, auditory perceptual assessment, K-VHI-10 and nodules size were compared before and after voice therapy. Voice therapy was conducted by speech-language pathologist and the mean number was 4.2. Results In acoustic analysis, Jitter, vF₀, vAm, Shimmer, NHR, and VTI were significantly decreased. F₀ was increased after voice therapy for women. 'Grade', 'Rough,' and 'Breathy' were significantly decreased in the GRBAS scale after voice therapy. In addition, K-VHI-10 and nodules size were significantly decreased. Conclusion VRM seems to be an effective voice therapy method in vocal nodules treatment. In VRM, especially, trial therapy is given motivation for vocal nodules treatments and self-practice has a continuous therapeutic effect in everyday life. VRM can be also applied to the voice therapy for other hyper-functional dysphonia.