• 인지과학
• /
• 제26권3호
• /
• pp.323-355
• /
• 2015

후기 한국어-영어 이중언어화자의 자소-음소 변환규칙(grapheme to phoneme conversion rule, GPC 규칙)에 따른 영어 규칙성 효과(regularity effect)가 단어수준과 하위단어수준에서 나타나는지 알아보기 위해 단어명명과제, 각운판단과제, 음소제거과제를 진행하였다. 전체 단어수준(whole word level)에서의 규칙 양상을 살펴보기 위해, [1] 영어단어명명과제(English word naming task)를 사용하였고, 단어 단위보다 하위 단계에서의 규칙성 효과를 알아보기 위해 [2] 라임판단 과제(rhyme judgement task)와 음소수준(phoneme level)에서의 과제인 [3] 음소탈락과제(phoneme deletion task)를 사용하였다. 실험 참가자들은 세 종류의 과제를 모두 수행하였고, 총 43명의 후기 이중언어화자가 실험에 참가하였다. 실험결과, 세 과제 모두에서 규칙성 효과가 나타나 한국어-영어 이중언어화자가 영어(L2) 단어 처리 시 GPC 규칙을 적극적으로 활용하고 있다는 사실을 확인하였다. 사후분석으로써 세 과제 사이의 상관분석을 진행한 결과, 단어명명과제와 라임판단과제 간 상관이 가장 높게 나타났다. 비록 영어 모국어 화자의 이전 연구결과와는 달리 라임판단과제와 단어읽기과제 간 상관이 높게 나타났지만, 이는 실험 참가자의 L2 능숙도가 모국어화자만큼 높지 않았기 때문인 것으로 보인다. 본 연구는 후기 한국어-영어 이중언어화자가 영어 GPC 규칙을 사용하여 영어단어읽기 처리를 하고 있음을 확인하였다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제20권12호
• /
• pp.682-687
• /
• 2014

한글 초성 질의는 내비게이션 시스템이나 모바일 기기와 같이 입력 환경에 제약이 있어 오류가 빈번한 인터페이스 상에서 사용자 편의성 향상을 위하여 제공되는 중요한 기능이다. 본 논문에서는 한글 문자열을 자소 단위로 분해하여 재배열하여 환형 문자열로 변환한 후, 확장된 버로우즈-휠러 변환을 이용하여 색인함으로써 초성 질의 탐색을 위한 시공간 효율적인 자료구조를 제안한다. 또한 실험을 통하여 기존 기법에 비하여 더 적은 공간만을 사용하면서도 보다 다양한 형태의 질의를 처리할 수 있으며, 특히 질의어의 길이가 짧고, 초성의 비율이 높을수록 탐색 속도가 향상됨을 확인하였다.

• 음성과학
• /
• 제11권2호
• /
• pp.193-210
• /
• 2004

In this paper, we develop a real time lip-synch system that activates 2-D avatar's lip motion in synch with an incoming speech utterance. To realize the 'real time' operation of the system, we contain the processing time by invoking merge and split procedures performing coarse-to-fine phoneme classification. At each stage of phoneme classification, we apply the support vector machine (SVM) to reduce the computational load while retraining the desired accuracy. The coarse-to-fine phoneme classification is accomplished via two stages of feature extraction: first, each speech frame is acoustically analyzed for 3 classes of lip opening using Mel Frequency Cepstral Coefficients (MFCC) as a feature; secondly, each frame is further refined in classification for detailed lip shape using formant information. We implemented the system with 2-D lip animation that shows the effectiveness of the proposed two-stage procedure in accomplishing a real-time lip-synch task. It was observed that the method of using phoneme merging and SVM achieved about twice faster speed in recognition than the method employing the Hidden Markov Model (HMM). A typical latency time per a single frame observed for our method was in the order of 18.22 milliseconds while an HMM method applied under identical conditions resulted about 30.67 milliseconds.

• 대한음성학회지:말소리
• /
• 제35_36호
• /
• pp.175-188
• /
• 1998

Database segmented and labeled up to phoneme level plays an important role in phonetic research and speech engineering. However, it usually requires manual segmentation and labeling, which is time-consuming and may also lead to inconsistent consequences. Automatic segmentation and labeling can be introduced to solve these problems. In this paper, we investigate a method to improve the performance of automatic segmentation and labeling system, where Spectral Variation Function(SVF), modification of silence model, and use of energy variations in postprocessing stage are considered. In this paper, SVF is applied in three ways: (1) addition to feature parameters, (2) postprocessing of phoneme boundaries, (3) restricting the Viterbi path so that the resulting phoneme boundaries may be located in frames around SVF peaks. In the postprocessing stage, positions with greatest energy variation during transitional period between silence and other phonemes were used to modify boundaries. In order to evaluate the performance of the system, we used 452 phonetically balanced word(PBW) database for training phoneme models and phonetically balanced sentence(PBS) database for testing. According to our experiments, 83.1% (6.2% improved) and 95.8% (0.9% improved) of phoneme boundaries were within 20ms and 40ms of the manually segmented boundaries, respectively.

• 대한음성학회지:말소리
• /
• 제48호
• /
• pp.127-139
• /
• 2003

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Korean speak Japanese. For this purpose we also develop phoneme recognizers for Korean and Japanese. Experimental results show that the machine scores of the proposed recognizer correlate with expert ratings well.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.154.2-154
• /
• 2001

This paper presented a adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when ...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.99.1-99
• /
• 2001

This paper presented an adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when only one adaptation utterance is used.

• 전자공학회논문지B
• /
• 제29B권9호
• /
• pp.17-26
• /
• 1992

This paper proposed an analysis method of common form for phonemes which is able to construct a Hangul syllable and designed the Choseong, Jungseong, and Jongseong phoneme fonts based on analized information. Also, It presents the algorithm which is able to construct the output of all Hangul syllables using 473 phoneme fonts. Through the experiment, an analized information and output algorithm could be applied to the design of Hangul fonts, effectively.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.395-398
• /
• 1994

In this paper the word recognition using sub-model based Hidden Markov Model was studied. Phoneme models were composed of 61 phonemes in therms of Korean language pronunciation characteristic. Using this, word model was maded by serial concatenation. But, in case of this phoneme concatenation, the second and the third phoneme of syllable are overlapped in distribution at the same time. So considering this, the method that combines the second and the third phoneme to one model was proposed. And to prevent the increase in number of model, similar phonemes were combined to one, and finially, 57 models were created. In experiment proper model structure of sub-model was searched for, and recognition results were compared. So similar recognition results were maded, and overall recognition rates were increased in case of using parameter tying method.

• 음성과학
• /
• 제11권3호
• /
• pp.83-93
• /
• 2004

The objectives of this study are to analyze Korean speakers' pronunciations of various Japanese /p/ patterns and to provide desirable pronunciation models. This is a part of an ongoing research that aims to propose a useful method of teaching Japanese pronunciation of /p/ to Koreans. The experimental data consist of /p/ phonemes in word initial, word medial, and 'yoon' positions. Yoon must be written in small size after a letter and it only makes a syllable with the preceding letter in Japanese. There were 22 different phoneme positions. They were pronounced by 48 Japanese majoring students (24 females and 24 males), who were in their twenties and were raised in Daejeon and vicinity. The individual pronunciations were collected and digitized into 528 files. The results show that Koreans pronounced the Japanese phoneme /p/ in a variety of ways, according to the auditory environments in which the phoneme was tested: as [ph] in word initial, [pp] or [ph] in word medial, and [ph] in 'yoon', unlike native speakers who pronounced Japanese /p/ as [ph] in word initial, [pp] in word medial and, and [pp] or [ph] in 'yoon'.