• 한국컴퓨터산업학회논문지
• /
• 제3권5호
• /
• pp.585-594
• /
• 2002

본 논문에서는 음성인식의 후처리를 위한 음가-표기 변환표의 생성과 구현에 관한 연구를 수행하였다. 음절 단위 음가를 인식하는 음성인식 시스템을 위한 후처리를 위하여 인식된 음가로 발음되는 표기 집합을 생성하는 표기 집합 생성기를 설계 구현하였다. 표준 발음법을 페트리넷으로 모델링하여 생성된 표기-음가 변환표를 기반으로 음가표기 변환표를 생성하였다. 음가-표기 변환표가 올바른 표기 집합을 생성함을 보이기 위하여 표기 집합 생성기를 설계 구현하고, 표준 발음법 예제와 발음법 사전에서 무작위로 추출된 단어에 대하여 실험한 결과 발성 이전의 표기가 포함된 올바른 표기 집합이 생성됨을 입증하였다.

• 음성과학
• /
• 제10권2호
• /
• pp.259-280
• /
• 2003

The paper discusses the way in which speech sounds are being evaluated and transcribed in various fields of speech sciences, and suggests ways for a more accurate transcription. The academic fields explored are of phonetics, speech processing, speech pathology, and foreign language education. The discussion centers on the International Phonetic Alphabet (IPA), most commonly used in these fields, and other less widely-accepted transcription conventions such as the TOnes and Break Indices (ToBI), the Speech Assessment Methods Phonetic Alphabet (SAMPA), an extension of the official Korean Romanization (KORBET), and the American-English transcription system in the TIMIT database (TIMITBET). These transcription conventions are dealt with Korean, English, and Korean-accented English. The paper demonstrates that each transcription can exclusively be recommended for a specific need from different academic fields. Due to its publicity, the IPA is best suited for phonetic evaluation in the fields of phonetics, speech pathology, and foreign language education. The rest of the transcriptions are useful for keyboard-inputting the phonetically evaluated data from all these fields as well as for sound transcription in speech engineering, because they use convenient letter symbols for typing, searching, and programming. Several practical suggestions are made to maintain the transcriptional efficiency and consistency to accommodate the intra-and inter-transcriber variability.

• 음성과학
• /
• 제9권1호
• /
• pp.149-171
• /
• 2002

After establishing the rules for the phonetic transcription in French, quantitative analysis on the given text, Waiting for Godot, is performed. Analyzing the text by investigating the influence of phoneme distribution is very interesting in the phonostylistic point of view. Since the phonetic transcription rules are useful for its automation, the rules are carefully established in this paper. From the results of the phonetic transcription, we can investigate the distribution of individual phonemes and the different phoneme groups between dialogues and scenery indications for various characters.

• 음성과학
• /
• 제10권4호
• /
• pp.23-40
• /
• 2003

This paper examines transcription of sounds from a phonological perspective. It has found that most of transcriptions have been done on a segmental basis alone, without consideration of the whole phonological systems and levels, and without a full understanding of the nature of the linguistic and phonetic alphabets. In a word, sound transcriptions have not been done on the basis of the phonology of the language and the alphabet. This study shows a phonological model for transcribing foreign and native sounds, suggesting ways of improving some of the current transcription systems such as the Hangeul transcription of loan words and the romanization of Hangeul, as well as the phonetic transcription of English and other foreign languages.

• 음성과학
• /
• 제9권1호
• /
• pp.63-75
• /
• 2002

This paper examines the principles of the International Phonetic Association and its Alphabet to see if the International Phonetic Alphabet (the IPA, for short) is adequate for transcribing sounds of a language like Korean. Special attention is given to 'broad transcription' and it has been found that the IPA is inadequate in representing the phonemes: there is no way to correctly transcribe phonemically the sounds of Korean with the current alphabet. A suggestion is given to help solve this problem and extend the IPA to accommodate all the different languages of the world.

• 한국지능시스템학회논문지
• /
• 제17권5호
• /
• pp.696-700
• /
• 2007

본 논문에서는 화자 독립 음소 인식기를 사용하는 음소열 기반 음성 인식 시스템의 성능을 향상시키는 새로운 방법을 제안하였다. 화자독립 음소 HMM을 사용하는 음성 인식 시스템은 입력 문장에 대한 음소열만을 사용하므로 저장 공간은 크게 줄일 수 있다. 그러나 시스템의 성능은 화자독립 모델을 사용하므로 발생하는 음소 오차 때문에 화자 종속 시스템보다 저하된다. 여기에서는 화자 적응 기술을 사용하여 화자독립 모델과 학습 데이터간의 불일치를 감소시키도록 음소열과 변환 벡터를 반복적으로 추정하는 학습 방법을 제안하였다. 화자 적응을 위한 변환 벡터를 추정하기 위하여 확률적 매칭 방법이 사용되었다. 실험은 전화선을 통하여 얻어진 데이터를 사용한 실험에서 기존 방법에 비하여 약 45%정도 오차가 감소되었다.

• The Journal of the Acoustical Society of Korea
• /
• 제20권4E호
• /
• pp.3-16
• /
• 2001

An ASCII encoding of Korean has been developed for extended phonetic transcription of the Speech Assessment Methods Phonetic Alphabet (SAMPA). SAMPA is a machine-readable phonetic alphabet used for multilingual computing. It has been developed since 1987 and extended to more than twenty languages. The motivating factor for creating Korean SAMPA (K-SAMPA) is to label Korean speech for a multilingual corpus or to transcribe native language (Ll) interfered pronunciation of a second language learner for bilingual education. Korean SAMPA represents each Korean allophone with a particular SAMPA symbol. Sounds that closely resemble it are represented by the same symbol, regardless of the language they are uttered in. Each of its symbols represents a speech sound that is spectrally and temporally so distinct as to be perceptually different when the components are heard in isolation. Each type of sound has a separate IPA-like designation. Korean SAMPA is superior to other transcription systems with similar objectives. It describes better the cross-linguistic sound quality of Korean than the official Romanization system, proclaimed by the Korean government in July 2000, because it uses an internationally shared phonetic alphabet. It is also phonetically more accurate than the official Romanization in that it dispenses with orthographic adjustments. It is also more convenient for computing than the International Phonetic Alphabet (IPA) because it consists of the symbols on a standard keyboard. This paper demonstrates how the Korean SAMPA can express allophonic details and prosodic features by adopting the transcription conventions of the extended SAMPA (X-SAMPA) and the prosodic SAMPA(SAMPROSA).

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.1-8
• /
• 1996

• 대한음성학회지:말소리
• /
• 제31_32호
• /
• pp.239-242
• /
• 1996

• 음성과학
• /
• 제7권1호
• /
• pp.143-169
• /
• 2000

This chapter presents an overview of Korean intonational structure and proposes a revised version of K -ToBI (Korean TOnes and Break Indices), a prosodic transcription convention for Seoul Korean. In the new version of K-ToBI, a tone tier is separated into two tiers: a phonological tone tier and a phonetic tone tier. A phonological tone tier labels tones marking the prosodic structure of an utterance, and a phonetic tone tier labels individual tones of an AP and an IP conforming to the surface pitch contour. Labelling surface tonal patterns will provide us data to test the underlying tonal patterns and to build phonetic implementation rules.