• IEIE Transactions on Smart Processing and Computing
• /
• 제5권3호
• /
• pp.215-221
• /
• 2016

This paper describes an automatic vowel sequence reproduction system for a talking robot built to reproduce the human voice based on the working behavior of the human articulatory system. A sound analysis system is developed to record a sentence spoken by a human (mainly vowel sequences in the Japanese language) and to then analyze that sentence to give the correct command packet so the talking robot can repeat it. An algorithm based on a short-time energy method is developed to separate and count sound phonemes. A matching template using partial correlation coefficients (PARCOR) is applied to detect a voice in the talking robot's database similar to the spoken voice. Combining the sound separation and counting the result with the detection of vowels in human speech, the talking robot can reproduce a vowel sequence similar to the one spoken by the human. Two tests to verify the working behavior of the robot are performed. The results of the tests indicate that the robot can repeat a sequence of vowels spoken by a human with an average success rate of more than 60%.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권11호
• /
• pp.713-720
• /
• 2015

컴퓨팅 기술과 네트워크의 발달로 인해, 정보 기기가 소형화되고 이동성이 강조되고 있다. 이에 따라 모바일 환경에서 작동 가능한 음성 인식 시스템에 대한 수요가 최근 급격히 증대되고 있다. 본 논문은 음소 기반 한국어 음성 인식 시스템의 일부로서, 한국어 모음 'ㅐ'에 대한 새로운 인식 방식을 제안한다. 제안하는 방식은 주파수 영역에서의 분석을 배제하고, 시간 영역에서의 시퀀스 패턴에 기반하여 인식을 수행함으로써, 계산 비용을 현저히 절감할 수 있다. 'ㅐ'의 전형적인 시퀀스 패턴들을 탐지하기 위한 세 가지 알고리즘이 제시되며, 이를 결합하여 최종 판별을 수행한다. 실험 결과를 통해, 제안하는 방식이 89.1%의 정확도로 모음 'ㅐ'를 인식할 수 있음을 확인하였다.

• 음성과학
• /
• 제7권4호
• /
• pp.169-186
• /
• 2000

This paper aims to confirm the mispronunciation of native Korean students due to the phonetic and phonological system differences between English and Korean, and to find the works-to-do by experiment. Many Korean students tend to differentiate the sounds of word-final stop consonants not by vowel duration or the allophones but by the phoneme of the consonant itself. In English, Stop sounds change through the conditions of the aspirated, unaspirated, or unreleased sounds. But in Korean they are not allophones of phonemes but distinct phonemes. Therefore, many Korean students are apt to add an extra vowel sound /i/ after the final stop consonant in the eve form due to both the unperception of the differences between the phonemes and the allophones of stop consonants, and the influence of the Korean sound-sequence relationship. Since the replacement of the allophones and extra vowel addition does not change the meaning, the importance was almost lost. Nevertheless, this kind of study is essential for the precise learning and the use of the English language.

• 말소리와 음성과학
• /
• 제12권3호
• /
• pp.15-23
• /
• 2020

This study examines the duration of Korean lax and tense stops in the prosodic word-medial position, their interactions with nearby segments, and the phonological implications of these interactions. It first examines the lengthening of consonants at the function of the short lax stop. Experiment 1 shows that the sonorant C1 is significantly longer before a short lax stop C2 than before a long tense stop. Experiment 2 shows that the short lax stop C1 cancels the contrast between the lax and tense obstruent at C2, making them appear as long tense obstruents (Post-Stop Tensing Rule). We suggest that such lengthening phenomena occur in Korean to robustly preserve the contrastive length difference between C and CC. Second, this study examines the vowel shortening, known as Closed-Syllable Vowel Shortening, before a long tense stop or before the consonant sequence. Experiment 3 suggests that it be interpreted as temporal adjustment to make the interval from the onset of a vowel to the onset of the following vowel of near-equal length. Conclusively, we suggest that Korean speech be planned and controlled with two specific intervals. One is the duration of contrastive consonant intervals between vowels, and the other is the duration from the onset of a vowel to the onset of the following vowel.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제20권11호
• /
• pp.567-572
• /
• 2014

최근 네트워크와 컴퓨팅 기술의 발달로 정보기기가 소형화되고 이동성이 중요시되면서 간편하게 제어할 수 있는 음성 인식에 대한 수요가 증가하고 있다. 본 논문은 음성 인식 시스템의 일부로써 한국어 음소 중 모음 'ㅏ' 인식에 대한 연구 결과를 제시한다. 음소는 음성을 구성하고 있는 최소단위로서 음성을 인식하는데 매우 중요한 역할을 한다. 그러나 각각의 음소들을 정확하게 인식하려면 발음의 다양성 등으로 인해 많은 어려움이 존재한다. 본 논문에서는 한국어 음소 중 모음 'ㅏ'를 인식하기 위한 간단하고도 새로운 방식을 제안한다. 제안된 'ㅏ' 인식 휴리스틱은 파형 시퀀스의 공통 특징 추출을 기반으로 이루어졌으며, 이는 기존의 복잡한 방법에 비해 간단하면서도 실험 결과 90% 이상의 성공률로 'ㅏ'를 인식하는 것을 확인하였다.

• 말소리와 음성과학
• /
• 제2권3호
• /
• pp.81-89
• /
• 2010

Korean and three other languages (English, Arabic, and Japanese) were compared with regard to the compensatory movements in a VC (Vowel and Consonant) sequence and word. For this, Korean data were collected from an experiment and the other languages' data from literature. All the test words of the languages had the same syllabic contexture, i.e., /CVCV(r)/, where C was an oral stop and intervocalic consonants were either bilabial or alveolar stops. The present study found that (1) Korean is most striking in the durational variations of segments (vowel and the following hetero-syllabic consonant); (2) unlike the three languages that show a constant sum of VC, Korean yields a three-way distinction in the length of VC according the type (lax unaspirated vs. tense unaspirated vs. tense aspirated) of the following stop consonant; (3) a durational constancy is maintained up to the word level in the three languages, but Korean word duration varies as a function of the feature tenseness of the intervocalic consonants; (4) consonant duration is proven to differentiate Korean the most from the other languages. It is suggested that the durational difference between a lax consonant and its tense cognate(s) and the degree of compensation between V and C are determined by the phonology in each language.

• 말소리와 음성과학
• /
• 제6권1호
• /
• pp.3-10
• /
• 2014

This study investigated whether Korean vowels, /ɨ/ and /u/, are distinctively perceived after a labial consonant given the fact that native and Sino-Korean nouns showed only vowel /u/ after a labial consonant while this pattern was massively broken by the recent introduction of loanwords. For this purpose, a perception experiment was conducted with $V_1C_1V_2$ sequences in which different vowels /a, i, u/ and consonants /p, t, k/ occurred in $V_1$ and $C_1$ before the target $V_2$, /ɨ/ and /u/. The data was produced by six speakers each from two different age groups, Age20 and Age40/50 in the read speech style. The results showed that consonant /p/ attracted significantly more responses of /u/ from /VCɨ/ sequences and significantly less responses of /u/ from /VCu/ sequence than the other consonants did in both age groups. Furthermore, Age20 group showed significantly less percentage of /u/ responses than Age40 group when the preceding consonant was /p/ regardless of the target vowel. We suggest therefore that unlike the traditional belief of labial assimilation, there is neutralization after a labial consonant in which vowels /ɨ/ and /u/ are often realized as any sound between two vowels, /ɨ/ and /u/. That is, this vowel change is not categorial but it rather produces an ambiguous stimulus which attracts different responses from different listeners. Ambiguous stimulus was produced due to coarticulatory efforts in speech production and perceptual compensation. We also argue that there is generational difference such that Age40/50 group speakers showed stronger tendency to produce /u/ after a labial consonant regardless of whether the target vowel was /ɨ/ or /u/.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권11호
• /
• pp.617-624
• /
• 2017

음성 인식은 HCI 분야에서 널리 사용되는 기술 중 하나이다. 가정 자동화, 자동 통역, 차량 내비게이션 등 음성 인식 기술이 적용될 수 있는 많은 응용들이 현재 개발되고 있다. 또한, 모바일 환경에서 작동 가능한 음성 인식 시스템에 대한 수요도 급속히 증대되고 있다. 본 논문은 한국어 음성 인식 시스템의 일부로서, 한국어 모음 'ㅡ'를 빠르게 인식할 수 있는 방안을 제시한다. 제안하는 방식은 주파수 영역 대신, 시간 영역에서 계산되는 지표인 벌크 지표를 사용하므로, 인식을 위한 계산 비용을 절감할 수 있다. 모음 'ㅡ'의 전형적인 시퀀스 패턴들을 표현하는 벌크 지표들에 대한 신경망 학습을 수행하며, 최종적인 인식을 위해 학습된 신경망을 사용한다. 실험 결과를 통해, 제안하는 방식이 모음 'ㅡ'를 88.7%의 정확도로 인식할 수 있음을 확인하였고, 인식 속도는 어절 당 0.74msec이다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2001년도 추계학술발표대회 논문집 제20권 2호
• /
• pp.25-28
• /
• 2001

본 논문에서는 조음 효과에 대처할 수 있는 반음절, 반음절 + 반음절 단위 HMM과 모음열 정보를 적용하여 연속 숫자 음성인식을 구현하였다. 모음열 정보를 적용하여 기준모델을 모음이 포함된 HMM단위로만 구성한 시스템과 모든 기준모델과 비교하는 시스템과 성능을 비교하였다. 인식실험결과 인식률의 향상으로 제안된 방법이 효율적임을 확인하였다.

• 음성과학
• /
• 제9권1호
• /
• pp.193-206
• /
• 2002

The aim of this study is to find out how the labiovelar onglide /w/ in English kwV sequences that have minimal pairs with kV sequences is pronounced differently among Korean EFL learners based on acoustic evidence. This study tries to identify /w/ sound in English kwV sequences through spectrograms and to examine the duration ratios of each segment in kwV words to compare the patterns of an English native speaker with those of Korean speakers of English. In spectrographic analyses, the complete deletion of /w/ and partial pronunciation of /w/ dubbed [$k^{w}$] were identified as well as the targetappropriate production of /w/. The general production patterns with respect to the duration ratios in English [kw] sequence words showed that the subjects who produced /w/ had similar ratio patterns that the native speaker had in that the vowel duration ratio in kwV sequences was shorter than that in kV sequences. By contrast, the subjects who deleted [w] had a long ratio of the onset [$k^{h}$] while the speaker with a partial pronunciation of /w/ had a long ratio of the following vowel.