• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1999년도 학술발표대회 논문집 제18권 2호
• /
• pp.361-364
• /
• 1999

한국어의 연속 음성 인식을 위하여 운율구 단위로 경계를 검출하는 연구가 진행되고 있다. 그 과정의 일부로서 본 연구에서는 여러 음향 특징들을 조합하여 연속음성에서 음절 경계의 검출하는 방법을 제시하였으며, 연속 음성으로부터 한국어 운율구인 강세구의 경계를 운율 특징만을 이용한 패턴 비교 방법을 이용하여 검출한 것과 비교 검토하였다. 그 결과, 패턴 비교 방법으로 검출한 강세구의 경계를 음절의 경계와 일치되도록 정렬해줄 필요가 있음을 알 수 있었다.

• 대한음성학회지:말소리
• /
• 제38호
• /
• pp.1-24
• /
• 1999

There is an indisputable connection between prosody and focus. The focal prominence in Korean, a prosodic realization of pitch prominence in an utterance, defines a focused constituent, the domain of which is identified by the Focus Identification Principle. To this is added the Basic Focus Rule which makes it possible to capture and interpret the focal domain, which can then be tested against the available context. The focal domain can be contextually made available by setting it off with information structure boundaries(I/S) identified by the Information Structure Identification Principle. The fragment of the utterance enclosed within the IS boundaries can be recognized as 'new' information with the help of the Focus Domain Identification Rule. Since information structures are pragmatically tied to semantic levels of grammatical systems, the Basic Focus Rule is now replaced by the Focal Prominence Principle ensuring the focal prominence within the focal domain. Close relationships exist between patterns of intonation and their expressiveness in terms of giving a pragmatically-oriented description of focus. This is particularly manifested in Korean sentences containing contrastiveness.

• 말소리와 음성과학
• /
• 제12권4호
• /
• pp.47-55
• /
• 2020

The current study was designed to investigate which type of phrase boundary tones high-intermediate Korean learners of English used in their spontaneous speech. These boundary tones were compared to those used in native speakers' spontaneous speech to examine whether the learners successfully acquired the use of boundary tones. To achieve this purpose, 10 Korean learners of English and four native speakers of English participated in the current study. The participants were asked to summarize the stories of short videos, and the tonal and the phrasing patterns of the obtained spontaneous speech were analyzed using Tone and Break Indices (ToBI) transcription conventions. The results indicated that both the native speakers and the Korean learners frequently marked their intonational phrase boundaries with high boundary tones. However, regarding the prosodic phrase positions within a sentence, Korean learners frequently used steep rising tones (i.e., H-H%) while native speakers used gradual rising tones (i.e., L-H%) for sentence-final intonational phrases. Overall, the findings suggested that high-intermediate Korean learners understood the forward-looking function of the high boundary tones and that they were able to make use of these tones to mark intonational phrases in their spontaneous speech.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.246-246
• /
• 1996

Purpose: Some of the properties of the prosodic phrasing and some acoustic and phonological effects of contrastive focus on the tonal pattern of Seoul Korean is explored based on a brief experiment of analyzing the fundamental frequency(=FO) contour of the speech of the author. Data Base and Analysis Procedures: The examples were chosen to contain mostly nasal and liquid consonants, since it is difficult to track down the formants in stops and fricatives during their corresponding consonantal intervals and stops may yield an effect of unwanted increase in the FO value due to their burst into the following vowel. All examples were recorded three times and the spectrum of the most stable repetition was generated, from which the FO contour of each sentence was obtained, the peaks with a value higher than 250Hz being interpreted as a high tone (=H). The result is then discussed within the prosodic hierarchy framework of Selkirk (1986) and compared with the tonal pattern of the Northern Kyungsang dialect of Korean reported in Kenstowicz & Sohn (1996). Prosodic Phrasing: In N.K. Korean, H never appears both on the object and on the verb in a neutral sentence, which indicates the object and the verb form a single Phonological Phrase ($={\phi}$), given that there is only one pitch peak for each $={\phi}$. However, Seoul Korean shows that both the object and the verb have H of their own, indicating that they are not contained in one $={\phi}$. This violates the Optimality constraint of Wrap-XP (=Enclose a lexical head and its arguments in one $={\phi}$), while N.K. Korean obeys the constraint by grouping a VP in a single $={\phi}$. This asymmetry can be resolved through a constraint that favors the separate grouping of each lexical category and is ranked higher than Wrap-XP in Seoul Korean but vice versa in N.K. Korean; $Align-x^{lex}$ (=Align the left edge of a lexical category with that of a $={\phi}$). (1) nuna-ka manll-ll mEk-nIn-ta ('sister-NOM garlic-ACC eat-PRES-DECL') a. (LLH) (LLH) (HLL) ----Seoul Korean b. (LLH) (LLL LHL) ----N.K. Korean Focus and Phrasing: Two major effects of contrastive focus on phonological phrasing are found in Seoul Korean: (a) the peak of an Intonatioanl Phrase (=IP) falls on the focused element; and (b) focus has the effect of deleting all the following prosodic structures. A focused element always attracts the peak of IP, showing an increase of approximately 30Hz compared with the peak of a non-focused IP. When a subject is focused, no H appears either on the object or on the verb and a focused object is never followed by a verb with H. The post-focus deletion of prosodic boundaries is forced through the interaction of StressFocus (=If F is a focus and DF is its semantic domain, the highest prominence in DF will be within F) and Rightmost-IP (=The peak of an IP projects from the rightmost $={\phi}$). First Stress-F requires the peak of IP to fall on the focused element. Then to avoid violating Rightmost-IP, all the boundaries after the focused element should delete, minimizing the number of $={\phi}$'s intervening from the right edge of IP. (2) (omitted) Conclusion: In general, there seems to be no direct alignment constraints between the syntactically focused element and the edge of $={\phi}$ determined in phonology; all the alignment effects come from a single requirement that the peak of IP projects from the rightmost $={\phi}$ as proposed in Truckenbrodt (1995).

• 한국음향학회지
• /
• 제17권5호
• /
• pp.12-21
• /
• 1998

이 연구는 몇 가지 음성적 특징들이 한국어 연속 음성에서의 운율단위의 운율 단서 로 사용되어질 수 있음을 보여 준다. 구 단위의 운율 이론 체계에서 한국어의 운율단위를 악센트구와 억양구로 정의한 전선아(1993)의 연구 결과를 연속음성 자료에 도입하면서 운율 경계에서의 음성적 특징들을 살펴보았다. 연구 결과 악센트구와 억양구말에서는 피치 패턴 과 경계성조의 변화 뿐 아니라 단위말 음절의 길이 증가 현상이 두드러짐을 알 수 있었다. 또 악센트구와 억양구초에서는 모음으로 시작하는 음절의 경우, 모음 시작부에서의 성문음 화가 특징으로 나타난다. 운율 경계에서의 이런 음성적 특징들은 운율단위를 구분짓는 단서 로 이용될 수 있으며 또한 한국어 연속음성의 운율적 패턴을 이해할 수 있게 한다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.542-547
• /
• 1996

Prosodic characteristics of natural speech, especially intonation, in many cases represent specific feelings of the speaker at the time of the utterance, with relatively vast variations of speaking styles over the same text. We analyzed a collected speech corpus, recorded with ten Slovene speakers. Interpretation of observed intonation contours was done for the purpose of modelling the intonation contour in synthesis process. We devised a scheme for modeling the intonation contour for different types of intonation units based on the results of analyzing intonation contours. The intonation scheme uses a superpositional approach, which defines the intonation contour as the sum of global (intonation unit) and local (accented syllables or syntactic boundaries) components. Near-to-natural intonation contour was obtained by rules, using only the text of the utterance as input.

• 말소리와 음성과학
• /
• 제2권4호
• /
• pp.39-49
• /
• 2010

The purpose of this paper is to examine how Chinese speakers realize Korean intonation phrase (IP) boundary tones in the reading of a Korean text. Korean IP boundary tones play various roles in speech communication. They indicate prosodic constituents' boundaries while simultaneously performing pragmatic and grammatical functions. In order to express and understand Korean utterances correctly, it is necessary to understand the Korean IP boundary tone system. To investigate the IP boundary tone produced by Chinese speakers, we have specifically examined the type of boundary tones, the degree of internal pitch modulation of boundary tones, and the pitch difference between penultimate syllables and boundary tones. The results of each analysis were compared to the IP boundary tones produced by Korean native speakers. The results show that IP boundary tones were realized higher than penultimate syllables.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 추계학술발표대회
• /
• pp.744-747
• /
• 2010

운율구 경계 예측은 TTS(Text-To-Speech) 엔진이 정확하고 자연스러운 음성합성을 하기 위해 꼭 필요한 기술이다. 하지만, 소프트웨어나 하드웨어적 자원을 많이 요구하는 기술이기 때문에 실행 환경의 제약을 많이 받는다. 본 논문에서는 소형 전자제품과 같이 제한된 환경에서도 안정적으로 실현되는 경량화 운율구 경계 예측 시스템의 개발 과정과 결과에 대하여 설명한다. 운율구 경계 예측 시스템의 필수 요소인 형태소 분석기의 경량화와 전통적인 규칙 기반 운율구 경계 예측 기술과 달리 품사 분석과 구문 분석이 필요하지 않은 운율구 경계 예측 기술을 소개한다.

• 한국음향학회지
• /
• 제20권3호
• /
• pp.24-33
• /
• 2001

이 논문에서는 대용량 음성 데이터베이스를 기반으로 하는 한국어 문장/음성변환시스템의 구현에 관해 기술한다. 기존 소량의 음성데이타를 이용하여 운율조절을 통해 합성하는 방식은 여전히 기계음에 가까운 합성음을 생성하고 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 대용량 음성 데이터베이스를 기반으로 하여 운율처리없이 합성단위 선정/연결에 의해 합성음질을 향상시키고자 한다. 대용량 음성 데이터베이스는 다양한 운율변화를 포함하도록 문장단위를 녹음하며 이로부터 복수개의 합성단위를 추출, 구축한다. 합성단위는 음성인식기를 훈련, 자동으로 음소분할하여 생성하며, 래링고그라프 신호를 이용하여 정교한 피치를 추출한다. 끊어 읽기는 휴지길이에 따라 4단계로 설정하고 끊어읽기 추정은 품사열의 통계정보를 이용한다. 합성단위 선정은 운율/스펙트럼 파라미터를 이용하여 비터비 탐색을 수행하게 되며 유클리디언 누적거리가 최소인 합성단위열을 선정/연결하여 합성한다. 또한 이 논문에서는 고품질 음성합성을 위해 특정 서비스 영역에 더욱 자연스러운 합성음을 생성할 수 있는 영역의존 음성합성용 데이터베이스를 제안한다. 구현된 합성시스템은 주관적 평가방법으로 명료도와 자연성을 평가하였고 그 결과 대용량 음성 데이터베이스를 기반으로한 합성방식의 성능이 기존 반음절단위를 사용한 합성방식보다 더 나은 성능을 보임을 알 수 있었다.

• 음성과학
• /
• 제7권2호
• /
• pp.193-208
• /
• 2000

This paper describes a multi-step method of intonation modeling for corpus-based Korean speech synthesizer. We selected 1833 sentences considering various syntactic structures and built a corresponding speech corpus uttered by a female announcer. We detected the pitch using laryngograph signals and manually marked the prosodic boundaries on recorded speech, and carried out the tagging of part-of-speech and syntactic analysis on the text. The detected pitch was separated into 3 frequency bands of low, mid, high frequency components which correspond to the baseline, the word tone, and the syllable tone. We predicted them using the CART method and the Viterbi search algorithm with a word-tone-dictionary. In the collected spoken sentences, 1500 sentences were trained and 333 sentences were tested. In the layer of word tone modeling, we compared two methods. One is to predict the word tone corresponding to the mid-frequency components directly and the other is to predict it by multiplying the ratio of the word tone to the baseline by the baseline. The former method resulted in a mean error of 12.37 Hz and the latter in one of 12.41 Hz, similar to each other. In the layer of syllable tone modeling, it resulted in a mean error rate less than 8.3% comparing with the mean pitch, 193.56 Hz of the announcer, so its performance was relatively good.