• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.592-595
• /
• 2022

한국어에서 한자어와 외래어가 차지하는 비중은 매우 높다. 일상어의 경우 한자어와 외래어의 비중이 약 53%, 전문어의 경우 약 92%에 달한다. 한자어나 외래어는 중국이나 다른 나라로부터 영향을 받아 한국에서 쓰이는 단어들이다. 한국어에서 사용되는 한자어와 외래어의 한글 표기과 원어 표기를 발음해보면, 발음이 상당히 유사하다는 것을 알 수 있다. 한자어인 도서관(图书馆)을 중국어로 발음해보면 t^hu.ʂu.kwan'로 해당 단어에 대한 한국 사람의 발음과 상당히 유사하다. 본 논문에서는 Source Length, Source IPA Length, Target Length, Target IPA Length, IPA Distance 등 총 5가지의 음성학적 특징을 고려한 한국어-중국어 한국어-영어 단어 기계번역 데이터 세트를 구축하고자 한다.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.174-182
• /
• 1996

In continuous speech recognition system, it is possible to implement the system which can handle unlimited number of words by using limited number of phonetic units such as phonemes. Dividing continuous speech into the string of tems of phonemes prior to recognition process can lower the complexity of the system. But because of the coarticulations between neiboring phonemes, it is very difficult ot extract exactly their boundaries. In this paper, we propose the algorithm ot extract short terms which can represent each phonemes instead of extracting their boundaries. The short terms of lower spectral change and higher spectral chang eare detcted. Then phoneme changes are detected using distance measure with this lower spectral change terms, and hgher spectral change terms are regarded as transition terms or short phoneme terms. Finally lower spectral change terms and the mid-term of higher spectral change terms are regarded s the represent each phonemes. The cepstral coefficients and weighted cepstral distance are used for speech feature and measuring the distance because of less computational complexity, and the speech data used in this experimetn was recoreded at silent and ordinary in-dorr environment. Through the experimental results, the proposed algorithm showed higher performance with less computational complexity comparing with the conventional segmetnation algorithms and it can be applied usefully in phoneme-based continuous speech recognition.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.93-102
• /
• 2005

In this paper, sub-stream based eigenvoice method is proposed to overcome the weak points of conventional eigenvoice and dimensional eigenvoice. In the proposed method, sub-streams are automatically constructed by the statistical clustering analysis that uses the correlation information between dimensions. To obtain the reliable distance matrix from covariance matrix for dividing into optimal sub-streams, MAP adaptation technique is employed to the covariance matrix of training data and the sample covariance of adaptation data. According to our experiments, the proposed method shows $41\%$ error rate reduction when the number of adaptation data is 50.

• 음성과학
• /
• 제11권3호
• /
• pp.181-192
• /
• 2004

The metrical structures in orally produced the poetry were generally analyzed by accent, metre and syllable. The purpose of this study is to investigate of metrical structures of Korean modem poetry using computer implemented speech analysis system. Two famous poet's poems confidential talk, Miloe and 'A buddhist dance, Sungmu' were selected for prosodic analysis. The informant is 60 years old professor in major of Korean and French poetry. The syllable structures of poems were analyzed primarily by vowel timbers, which can classified compact and diffuse vowels according to the distance of F2-F1. The perception cues of consonants were analyzed by VOT and tensity features of articulation. Rhythm is classified by dactyl, anapest, trochee, spondee and iambic. As a result, syllable structures of Korean modem poetry were mainly CV and CVC and the reading times of each lines were 3-4sec for 12 and 15 syllables. Main metre of Korean modem poems constructed the Imbic and Anapest. The break of each lines were demarcated by grammatical structure or meaning rather than phonetic structures.

• 대한음성학회지:말소리
• /
• 제64호
• /
• pp.155-169
• /
• 2007

Discrimination between speech and music is important in many multimedia applications. In our previous work, focusing on the spectral change characteristics of speech and music, we presented a method using the mean of minimum cepstral distances (MMCD), and it showed a very high discrimination performance. In this paper, to further improve the performance, we propose to employ time-averaged MFCC in computing the MMCD. Our experimental results show that the proposed method enhances the discrimination between speech and music. Moreover, the proposed method overcomes the weakness of the conventional MMCD method whose performance is relatively sensitive to the choice of the frame interval to compute the MMCD.

• 대한음성학회지:말소리
• /
• 제64호
• /
• pp.1-14
• /
• 2007

The purpose of this study was to examine the acoustic perception different by formants change for profoundly hearing impaired children with cochlear implants. The subjects were 10 children after 15 months of experience with the implant and mean of their chronological age was 8.4 years and Standard deviation was 2.9 years. The ability of auditory perception was assessed using acoustic-synthetic vowels. The acoustic-synthetic vowel was combined with F1, F2, and F3 into a vowel and produced 42 synthetic sound, using Speech GUI(Graphic User Interface) program. The data was deal with clustering analysis and on-line analytical processing for perception ability of acoustic synthetic vowel. The results showed that auditory perception scores of acoustic-synthetic vowels for cochlear implanted children were increased in F2 synthetic vowels compaire to those of F1. And it was found that they perceived the differences of vowels in terms of distance rates between F1 and F2 in specific vowel.

• 대한음성학회지:말소리
• /
• 제65호
• /
• pp.153-168
• /
• 2008

We propose a new method to apply shape analysis techniques to a computational auditory scene analysis (CASA)-based speech separation system. The conventional CASA-based speech separation system extracts speech signals from a mixture of speech and noise signals. In the proposed method, we complement the missing speech signals by applying the shape analysis techniques such as labelling and distance function. In the speech separation experiment, the proposed method improves signal-to-noise ratio by 6.6 dB. When the proposed method is used as a front-end of speech recognizers, it improves recognition accuracy by 22% for the speech-shaped stationary noise condition and 7.2% for the two-talker noise condition at the target-to-masker ratio than or equal to -3 dB.

• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.85-97
• /
• 2006

This paper suggests an algorithm that can estimate the direction of the sound source in real time. The algorithm uses the time difference and sound intensity information among the recorded sound source by four microphones. Also, to deal with noise of robot itself, the Kalman filter is implemented. The proposed method can take shorter execution time than that of an existing algorithm to fit the real-time service robot. Also, using the Kalman filter, signal ratio relative to background noise, SNR, is approximately improved to 8 dB. And the estimation result of azimuth shows relatively small error within the range of ${\pm}7$ degree.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 추계학술대회 발표논문집
• /
• pp.142-145
• /
• 2006

Discrimination between speech and music is important in many multimedia applications. Previously we proposed a new parameter for speech/music discrimination, the mean of minimum cepstral distances (MMCD), and it outperformed the conventional parameters. One weakness of it is that its performance depends on range of candidate frames to compute the minimum cepstral distance, which requires the optimal selection of the range experimentally. In this paper, to alleviate the problem, we propose a multi-dimensional MMCD parameter which consists of multiple MMCDs with different ranges of candidate frames. Experimental results show that the multi-dimensional MMCD parameter yields an error rate reduction of 22.5% compared with the optimally chosen one-dimensional MMCD parameter.

• 대한음성학회지:말소리
• /
• 제60호
• /
• pp.191-201
• /
• 2006

Discrimination between speech and music is important in many multimedia applications. Previously we proposed a new parameter for speech/music discrimination, the mean of minimum cepstral distances (MMCD), and it outperformed the conventional parameters. One weakness of MMCD is that its performance depends on range of candidate frames to compute the minimum cepstral distance, which requires the optimal selection of the range experimentally. In this paper, to alleviate the problem, we propose a multi-dimensional MMCD parameter which consists of multiple MMCDS with combination of different candidate frame ranges. Experimental results show that the multi-dimensional MMCD parameter yields an error rate reduction of 22.5% compared with the optimally chosen one-dimensional MMCD parameter.