• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.216-219
• /
• 2003

본 논문은 최소한의 형태소 정보를 이용한 자동 발음열 생성 시스템을 제안한다 일반적으로 발음열 생성 시스템은 입력된 문장에 대하여 형태소 단위로 분석한 다음, 각 형태소와 형태소의 결함 관계를 고려한 음운 규칙을 적용함으로써 상응하는 발음열을 생성한다. 지금까지의 연구는 이러한 발음열 생성시의 형태소 분석에 관하여 그 범위에 관한 연구 없이, 가능한 최대한의 분석을 상정하고 있다. 본 논문은 한국어 음운현상을 체계적인 텍스트 분석을 통하여 모든 형태론적 음운론적인 환경에서 가능한 모든 음운현상을 분류하여 발음열 생성시에 실제로 필요한 형태소 분석의 범위를 규명하는 것을 그 목적으로 한다. 음운 현상을 분석하기 위해 사용한 텍스트 자료로는 어휘가 중복되지 않으면서도 많은 종류의 어휘가 수록된 5만 여 어휘의 연세한국어사전과 2200 여 개의 어미와 조사를 수록한 어미조사사전을 이용하였다. 이와 같이 텍스트를 분석한 결과, 음운현상은 규칙적인 음운 현상과 불규칙적인 음운현상으로 나뉘는데, 이 가운데 형태소 정보가 필요한 형태음운규칙으로는 두 가지가 있으며, 이러한 형태음운규칙을 위한 형태소 분석의 범위로는 세세한 분류를 필요로 하지 않는 최소한의 정보로 가능함을 보인다. 이러한 체계적인 분석을 기반으로 제안하는 자동 발음열 생성 시스템은 형태음운규칙과 예외규칙, 그리고 일반음운 규칙으로 구성된다. 본 시스템에 대한 성능 실험은 PBS 1637 어절과 ETRI 텍스트 DB 19만 여 어절을 이용하여 99.9%의 성능결과를 얻었다.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.75-83
• /
• 1999

This paper proposes a new F0 contour model for intonation control in speech synthesis. We assume that the F0 contour of an utterance can be described using a sequence of time-overlapping events, which determine the fluctuation of a given F0 contour, described by asymmetric Gaussian functions. In addition, We propose a parameter estimation algorithm for the proposed model. The proposed model is not developed with a particular phonological theory in mind, and can be used in both F0 contour analysis and synthesis. For testing our F0 model, we collected 500 sentences from various genres and built a corresponding speech corpus uttered by a professional female announcer. As n result of F0 resynthesis experiment using the proposed model, the RMSE was 7.87Hz for given speech corpus.

• Journal of the Korean Society for Railway
• /
• v.14 no.3
• /
• pp.228-233
• /
• 2011

This paper presented the method about the Implementation of Speech Recognition based on phoneme considering the phonological characteristic for Korean Subway Station Names. The Pronunciation dictionary considering PLU set and phonological variations with four Case in order to select the optimum PLU used for Speech Recognition based on phoneme for Korean Subway Station Names was comprised and the recognition rate was estimated. In the case of the applied PLU, we could know the optimum recognition rate(97.74%) be shown in the triphone model in case of considering the recognition unit division of the initial consonant and final consonant and phonological variations.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.198-206
• /
• 1996

Using eighteen text materials from various goners of present-day Japanese, we collected phonologically reduced forms frequently observed in conversational Japanese, and classified them in search of unified explanation of phonological reduction phenomena. We found 7,516 cases of reduced forms which we divided into 43 categories according to the types of phonological changes they have undergone. The general tendencies ale that deletion and fusion of a phoneme or an entire syllable takes place frequently, resulting in the decrease in the number of syllable. Typical examples frequently observed throughout the materials are : $~/noda/{\rightarrow}~/nda/,{\;}-/teiru/{\rightarrow}~/teru/,{\;}~/dewa/{\rightarrow}~/zja/,{\;}~/tesimau/{\rightarrow}~/cjau/$. From morphosyntactic point of view phonological reduction often occurs at the NP and VP morpheme boundaries. The following findings are drawn from phonological observations of reduction. (1) Vowels are more easily deleted than consonants. (2) Bilabials(/m/, /b/, and /w/ are the most likely candidates for deletion. (3) In a concatenation of vowels, closed vowels are absorbed into open vowels, or two adjacent vowels come to create another vowel, in which case reconstruction of the original sequence is not always predictable. (4) Alveolars are palatalized under the influence of front vowels. (5) Regressive assimilation takes place in a syllable starting with ill, changing the entire syllable into phonological choked sound or a syllabic nasal, depending on the voicing of following phoneme.

• Speech Sciences
• /
• v.8 no.4
• /
• pp.229-241
• /
• 2001

Using eighteen texts from various genera of present-day Japanese, I collected phonologically reduced forms frequently observed in conversational Japanese, and classified them in search of a unified. explanation of phonological phenomena. I found 7,516 cases of reduced forms which I divided into 43 categories according to the types of phonological changes they have undergone. The general tendencies are that deletion and fusion of a phoneme or an entire syllable takes place frequently, resulting in the decrease in the number of syllables. From a morphosyntactic point of view, phonological reduction often occurs at the NP and VP morpheme boundaries. The following findings are drawn from phonetical observations of reduction. (1) Vowels are more easily deleted than consonants. (2) Bilabials ([m], [b], and [w]) are the most likely candidates for deletion. (3) In a concatenation of vowels, closed vowels are absorbed into open vowels, or two adjacent vowels come to create another vowel, in which case reconstruction of the original sequence is not always predictable. (4) Alveolars are palatalized under the influence of front vowels. (5) Regressive assimilation takes place in a syllable starting with [r], changing the entire syllable into a phonological choked sound or a syllabic nasal, depending on the voicing of the following phoneme.

• Annual Conference on Human and Language Technology
• /
• 2006.10e
• /
• pp.183-188
• /
• 2006

본 논문에서 위치 정보 데이터란 텔레메틱스 분야의 응용을 위하여 웹상에서 수집한 Point-of-Interest (POI) 데이터로서 행정구역 및 지명 인명, 상호명과 같은 위치 검색에 사용되는 어휘로 구성된다. 본 논문은 음성 인식 시스템을 구성하는 발음 사전의 개발에 관한 것으로 250k 위치 정보데이터로부터 운율어를 이용하여 불규칙 발음과 발음 변이를 포함하는 가능한 모든 발음을 생성하는 방법을 제안하는 것을 목적으로 한다. 원래 모든 POI 는 한 번씩만 데이터에 포함되어 있으므로, 그 가운데 불규칙 발음을 포함하는 POI를 검출하거나 발음을 생성하기 위해서는 각각의 POI 하나하나를 일일이 검토하는 방법밖에 없는데, 대부분의 POI 가 복합명사구로 이루어졌다는 점에 착안하여 운율어를 이용한 결과, 불규칙 발음 검출과 다중 발음 생성을 효율적으로 수행할 수 있었다. 이러한 연구는 음성처리 영역에서는 위치정보데이터의 음성인식 성능을 향상하는 데 직접적인 기여를 할 수 있고, 무엇보다도 음성학과 음운론 이론을 음성 인식 분야에 접목한 학제적 연구로서 그 의미가 있다고 할 수 있다.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.2
• /
• pp.215-228
• /
• 1995

Despite their importance in language, there have been relatively few computational studies in understanding words. This paper describes how neural networks can learn to perceive and produce words. Most traditional linguistic theories presuppose abstract underlying representations (UR) and a set of explicit rules to obtain the surface realization. There are, however, a number of questions that can be raised regarding this approach: (1) assumption of URs, (2) formation of rules, and (3) interaction of rules. In this paper, it is hypothesized that rules would emerge as the generalizations the network abstracts in the process of learning to associate forms with meanings of the words. Employing a simple recurrent network, a series of simulations on different types of morphophonemic processes was run. The results of the simulations show that this network is capable of learning to perceive whether words are in basic from or in inflected form, given only forms, and to produce words in the right form, given arbitrary meanings, this eliminating the need for presupposing abstract URs and rules.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.6
• /
• pp.434-442
• /
• 2003

Software internationalization, the process of making software easier to localize for specific languages, has deep implications when applied to speech technology, where the goal of the task lies in the very essence of the particular language. A greatdeal of work and fine-tuning has gone into language processing software based on ASCII or a single language, say English, thus making a port to different languages difficult. The inherent identity of a language manifests itself in its lexicon, where its character set, phoneme set, pronunciation rules are revealed. We propose a decomposition of the lexicon building process, into four discrete and sequential steps. For preprocessing to build a lexical model, we translate from specific language code to unicode. (step 1) Transliterating code points from Unicode. (step 2) Phonetically standardizing rules. (step 3) Implementing grapheme to phoneme rules. (step 4) Implementing phonological processes.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.35-43
• /
• 2001

Many speech recognition systems have used pronunciation lexicon with possible multiple phonetic transcriptions for each word. The pronunciation lexicon is of often manually created. This process requires a lot of time and efforts, and furthermore, it is very difficult to maintain consistency of lexicon. To handle these problems, we present a model based on morphophon-ological analysis for automatically generating Korean pronunciation variants. By analyzing phonological variations frequently found in spoken Korean, we have derived about 700 phonemic contexts that would trigger the multilevel application of the corresponding phonological process, which consists of phonemic and allophonic rules. In generating pronunciation variants, morphological analysis is preceded to handle variations of phonological words. According to the morphological category, a set of tables reflecting phonemic context is looked up to generate pronunciation variants. Our experiments show that the proposed model produces mostly correct pronunciation variants of phonological words. Then we estimated how useful the pronunciation lexicon and training phonetic transcription using this proposed systems.

• Cross-Cultural Studies
• /
• v.42
• /
• pp.241-260
• /
• 2016

The purpose of this article is to represent the types of advertising in the modern Russian language as 'Play of Words' (игра слов). The causal reason for this phenomenon is studied from the result of certain characteristics of advertising. The definition and characteristics of the language of the advertisement are analyzed in achieving the goal, as these factors reveal how language is used to maximize the effectiveness of the advertising. Academic research is needed in the collaborative fields of linguistics, psychology, economics, sociology, marketing, literature, art, and music. Modern advertisement is mixed with semiotic objects that consist of display, sound, and texts. While this study is not complete, the acknowledgement of the phenomenon 'Play of Words' between the creators of advertising and the consumer is undeniable. On one hand, advertising is recognized by linguists as the main factor that destroys the literary language. It represents the distortion of a standard language norm, as opposed to formal linguistic means used in advertising. In this research, we pay attention to the frequent use of foreign language borrowings and incorrect representation of foreign words, slang and jargon, that occur in misspelled usage of literary norms. The features that are revealed in this article are helpful to understand the purpose of advertising.