• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2228-2231
• /
• 2003

In this paper, a transcoding algorithm for the Selectable Mode Vocoder (SMV) and the G.723.1 speech coder via direct parameter transformation is proposed. In contrast to the conventional tandem transcoding algorithm, the proposed algorithm converts the parameters of one coder to the Other Without going through the decoding md encoding process. The proposed algorithm is composed of four parts: the parameter decoding, line spectral pair (LSP) conversion, pitch period conversion, excitation conversion and rate selection. The evaluation results show that the proposed algorithm achieves equivalent speech quality to that of tandem transcoding with reduced computational complexity and delay.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.5
• /
• pp.71-81
• /
• 1997

This paper proposes noun and affix extraction methods using conjunctive information for making an automatic indexing system thorugh morphological analysis and syntactic analysis. The korean language has a peculiar spacing words rule, which is different from other languages, and the conjunctive information, which is extracted from the rule, can reduce the number of multiple parts of speech at a minimum cost. The proposed algorithms also solve the problem that one word is seperated by newline charcter. We show efficiency of the proposed algorithms through the process of morhologica analyzing.

• MALSORI
• /
• no.37
• /
• pp.23-48
• /
• 1999

To improve the performance of automatic labelling system, the context-dependent demiphone unit was proposed. A phone is divided into two parts: a left demiphone that accounts for the left side coarticulation and a right demiphone that copes with the right side context. Demiphone unit provides a better training of the transition between phones. In this paper, If the length of the phone is less than 120 msec, it is split into two demiphones. If the length of the phone is greater than 120 msec, it is divided into three parts. In order to evaluate the performance of the system, we use 452 phonetically balanced words(PBW) database for training and testing phoneme models. According to the experiment, the system using proposed demiphone unit compared with that using old demiphone unit gains 3.83% improved result(71.63%) within 10ms of the duo boundary, and 2.20% improved result(86.41%) within 20ms of the true boundary.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.460-462
• /
• 2005

사용자가 원하는 점보를 찾아주는 정보 검색 시스템은 최근까지 않은 연구가 이루어지고 있다. 일반적인 검색 엔진에서는 질의문이나 문서들을 색인할 때 영사를 중심으로 색인을 한다. 본 논문에서는 사용자가 한단어로 질의하지 않고 서술문 형식으로 질의를 할 경우 사용자가 원하는 정확한 정보를 검색해 내기 위하여 품사에 관계없이 사용자가 선택한 질의어들과 문서에서 나타나는 모든 용어들을 중요하다고 보고 명사만 이용하는 경우와 모든 품사를 이용하는 경우로 나누어 실험해 보았다.

• Cross-Cultural Studies
• /
• v.42
• /
• pp.371-392
• /
• 2016

This study analyzed the aspect of the decision of the Korean part of speech and the properties of the grammatical items based on "韓語通" which was published in 1909. "韓語通" is a Korean grammar book written by 前間恭作 who also published "校訂交隣須知" in 1904. "韓語通" is known for influencing of 'Otsuki grmmar(大槻 文法),' dividing Korean part of speech into eleven. Based on 'mood' and 'voice' we can assume that "韓語通" adopted Otsuki's grammar. '存在詞' is another clue that "韓語通" adopted Yamada's grammar. However, 前間恭作 persisted that Korean language is different from Japanese language. This view is different from 寶迫繁勝, 高橋亨, 藥師寺知? etc. This study tried to investigate the interchange of the two languages in historical study of Korean and Japanese linguistics during modern and contemporary period. For this purpose, we searched the aspect of the part of speech and analyzed the grammar items. In conclusion, we was able to light on how Japanese scholars approached to Korean grammar system in late 19th and early 20th centuries.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1208-1221
• /
• 2006

In this paper, we implement an AAC(Augmentative and Alternative Communication) system based on image dictionary in order that speech defectives can easily communicate their opinion to others by using images. Normally, those who have a speech defect use only a few limited words to express their intentions and it is an effective way to use images in their communication because they have a difficulty in speaking. Therefore we make verbal images of verb and adjective that play an important role in expressing the speaker's intention, define pattern of semantic relation between the verbal images and noun images, and construct the image dictionary. In this AAC system, when a user clicks a verbal image, the system generates a sentence by selecting noun images which are component parts of corresponding pattern based on semantic relation with the verbal image. We evaluate the implemented system by how efficiently children of speech defect can express their intention and the result shows more than 70% of success rate in communication.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2002.05a
• /
• pp.76-81
• /
• 2002

인터넷의 발달 등으로 많은 정보들이 문서화되기도 하고 그런 정보들이 공유되고 있는 지금, 언어학이나 전산학의 요구를 함께 충족시킬 수 있는 문법 모델 개발의 필요성이 극대화되고 있다. 이 글은 한국어 품사 분류에 대해서 국어학과 전산학에서의 처리 방법과 결과를 검토하고 정리하여 우리말의 특성을 잘 설명하면서도 국어를 전산 처리하는데도 도움을 줄 수 있는 품사분류를 제안하는데 그 목적이 있다. 한국어의 특성을 고려하여 음운, 형태, 통 어, 의미 정보를 함께 처리할 수 있는 어휘부 중심의 문법인 HPSG의 모형을 도입하여 한국어 품사 분류를 정보 전달에 기반을 두어 자질 체계와 통합 연산을 핵심으로 기술하려고 한다. 문법기술은 주로 자질 구조를 속성과 값의 행렬인 AVM(attribute-value matrices)으로 제시할 것이다.

• Journal of Biomedical Engineering Research
• /
• v.34 no.1
• /
• pp.8-13
• /
• 2013

Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4) music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.

• 재활복지
• /
• v.21 no.2
• /
• pp.217-231
• /
• 2017

We have to consider two parts of the evaluation and treatment for the patients with head and neck burns. The primary consideration is swallowing function for nutrition supply for them and the next is speech function for efficient communication and aesthetic impression of them. The purpose of this study is to summarize the preliminary questions of Communication Screening Protocols which can help understand comprehensively on swallowing disorder, motor speech disorder and voice disorder of patients with head and neck burns. We divided the evaluation into 4 evaluation areas including 'oral mechanism', 'respiration/voice', 'articulation', and 'swallowing' by referring to overseas studies dealing with various communication disorders caused by burns, and prepared the final questionnaires by conducting the content validity verification by five expert (speech & language pathologist). The range of Content Validity Index was shown relatively appropriate with .50~.84. There was a conflict of opinions in experts whether the items in the areas of respiration/voice and swallowing may be appropriate, whereas there was no different view of the oral mechanism and articulation area. Through the different characteristics of communication difficulties of patients with head and neck burns, we expect it will be modified appropriately according to the patients through evaluation of burn patients by type and severity.

• Speech Sciences
• /
• v.1
• /
• pp.113-135
• /
• 1997

This study aims to present some notes on the French syllabic structure based on the relation between the intonation pattern and the stressed syllable. The recent phonetico-phonological study is mainly focussed on the notion of syllable. However it is quite difficult to analyse the syllable structure because of its complexity. In this paper I have tried to analyse the French syllabic structure both in phonetics and in phonology. This paper contains three parts. First of all, in section 2, the notion of syllable and the French prosodic phenomena are reviewed phonetically, and is phonologically focused on the intonation pattern. Secondly, in section 3, I have analyzed the relation between the intonation. pattern and the stressed syllable in French based on CSL analyses. Finally, in section 4, I have suggested some syllabic structure patterns in French based on the analyses in section 3. This. is an attempt to further the inter-disciplinary study between phonetics and phonology, and also an attempt to settle on a model of phonological French syllabic structure. I have left the application of the result of this study as a future subject to study. But still, the result of this study can serve as a basic reference for those who are studying French and for students who are would like to learn about French syllabic structure.