• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2000년도 7월 학술대회지
• /
• pp.105-116
• /
• 2000

How to teach intelligible, communicative pronunciation is a continuous question in the English education. Without good input, we can not expect good output. However, in EFL situation, it is very difficult to input the good English pronunciation, therefore, we have to find out the efficient and effective material for teaching pronunciation. One of the materials is song, because songs contain the linguistic and cultural traits of the language. The purpose of this paper is to clarify the reason why songs are good for teaching pronunciation. Koreans, who are syllable timed language users, have difficulties in English pronunciation of stress, rhythm, consonants cluster, linking or blending in connected speech. The 134 songs from wee sing are analyzed for how these traits show in songs. The result shows that we can acquire the traits easily and naturally through songs. And a lesson plan is offered as an example for teaching songs.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 추계학술대회 발표논문집
• /
• pp.24-27
• /
• 2006

This paper describes how a domain dependent pronunciation lexicon is generated and optimized for Korean large vocabulary continuous speech recognition(LVCSR). At the level of lexicon, pronunciation variations are usually modeled by adding pronunciation variants to the lexicon. We propose the criteria for selecting appropriate pronunciation variants in lexicon: (i) likelihood and (ii) frequency factors to select variants. Our experiment is conducted in three steps. First, the variants are generated with knowledge-based rules. Second, we generate a domain dependent lexicon which includes various numbers of pronunciation variants based on the proposed criteria. Finally, the WERs and RTFs are examined with each lexicon. In the experiment, 0.72% WER reduction is obtained by introducing the variants pruning criteria. Furthermore, RTF is not deteriorated although the average number of variants is higher than that of compared lexica.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.191-194
• /
• 2002

The final purpose of this paper is the enhancement of speech recognition rate under the matched telephone environment between training data and test data. To analyze the effect by the distortion of the changing telephone channel on every call, MFCC is used as the feature parameter and CMN, RTCN, and RASTA are used as channel compensation techniques. For each case, the variation of feature parameters of all phones is analyzed. And, we find recognition rates according to each compensation method using the continuous HMM recognizer, and examine the relationship between variation and recognition rate.

• 음성과학
• /
• 제8권4호
• /
• pp.1-15
• /
• 2001

This paper describes the effect of new recognition unit, a unit based on semisyllable, and its post processing method. A recognition unit based on semi-syllable expresses Korean connected digit's coarticulation effect. An existing method using semi-syllable limits next models, derived from current recognized models, to make complete connected digit sequence. However, this paper uses a new method to make complete connected digit sequence. The new post-processing method recognizes isolated digit words which include digits sequence from the digit combinations being able to occur from current recognized semi-syllable sequence. This method gives an improved accuracy rate than that of existing method. This new post processing provides two advantages. 1) It corrects current mis-recognized semi-syllable unit. 2) When people say each digit, they say it without regard to saying duration.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.33-36
• /
• 2002

We implemented a robust Korean broadcast news transcription system for out-of-vocabulary (OOV), tested its performance. The occurrence of OOV words in the input speech is inevitable in large vocabulary continuous speech recognition (LVCSR). The known vocabulary will never be complete due to the existence of for instance neologisms, proper names, and compounds in some languages. The fixed vocabulary and language model of LVCSR system directly face with these OOV words. Therefore our Broadcast news recognition system has an offline OOV update module of language model and vocabulary to solve OOV problem and selects morpheme-based recognition unit (so called, pseudo-morpheme) for OOV robustness.

• 대한전기학회논문지
• /
• 제40권4호
• /
• pp.360-373
• /
• 1991

Since 70's, efficient speech recognition methods such as HMM or DTW have been introduced primarily for speaker dependent isolated words. These methods however have confronted with difficulties in recognizing continuous speech. Since early 80's, there has been a growing awareness that neural networks might be more appropriate for English and Japanese phoneme recognition using neural networks. Dealing with only a part of vowel or consonant set, Korean phoneme recognition still remains on the elementary level. In this light, we develop a system based on neural networks which can recognize major Korean phonemes. Through experiments using two neural networks, SOFM and TDNN, we obtained remarkable results. Especially in the case of using TDNN, the recognition rate was estimated about 93.78% for training data and 89.83% for test data.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.75-78
• /
• 2003

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon for Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished pronunciation variation rules according to the locations such as within a morpheme, across a morpheme boundary in a compound noun, across a morpheme boundary in an eojeol, and across an eojeol boundary. In 33K-morpheme Korean CSR experiment, an absolute improvement of 1.16％ in WER from the baseline performance of 23.17％ WER is achieved by modeling cross-morpheme pronunciation variations with a context-dependent multiple pronunciation lexicon.

• ETRI Journal
• /
• 제41권1호
• /
• pp.109-116
• /
• 2019

This paper explores new techniques that are based on a hidden-layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular-value decomposition (SVD) are utilized because they are effective at reducing adaptive parameters. However, a matrix decomposition is computationally expensive when using online services. We propose the use of an extended diagonal linear transformation method to minimize adaptation parameters without SVD to increase the performance level for tasks that require smaller degrees of adaptation. In Korean large vocabulary continuous speech recognition (LVCSR) tasks, the proposed method shows significant improvements with error-reduction rates of 8.4% and 17.1% in five and 50 conversational sentence adaptations, respectively. Compared with the adaptation methods using SVD, there is an increased recognition performance with fewer parameters.

• 대한전자공학회논문지
• /
• 제24권2호
• /
• pp.274-279
• /
• 1987

In this paper, we describe a new algorithm for extracting nasal sound in continuous speech. We obtain pitches by using Area Comparison Method and extract nasal sound by comparing the area of G-peak and the area of side peak in one pitch interval. By using this method, the process can be speeded up. Therefore realtime processing is possible with a general microprocessor.

• 한국음향학회지
• /
• 제18권6호
• /
• pp.49-56
• /
• 1999

결정 트리 기반 상태 공유 방법은 HMM을 사용하는 많은 연속 음성 인식 시스템에서 강인하고 정확한 문맥 종속 음향 모델링 뿐만 아니라 훈련 중에는 나타나지 않은 모델들의 합성을 위하여 널리 사용되고 있다. 음성 결정 트리를 구성하기 위한 표준적인 방법은 단일 가우시안 트라이폰 모델을 이용한 1계층 프루닝 만을 사용하고 있다. 본 논문에서는 더욱 정교한 음향 모델링을 통하여 인식 성능 향상을 도모하기 위하여 새로운 2가지 접근 방법 즉, 2계층 결정 트리와 복수 혼합 결정 트리를 제안한다. 2계층 결정 트리는 상태 공유와 혼합 가중치 공유를 위하여 2계층 프루닝을 수행하며, 두 번째 계층을 사용하여 공유 상태들도 음성 문맥의 유사도에 따라서 서로 다른 가중치들을 사용할 수 있다. 두 번째 제안된 방법 에서는 훈련 과정 즉, 혼합 분할 및 재추정 과정과 함께 음성 결정 트리가 계속 갱신되어 진다. 복수 혼합 결정 트리를 구성하기 위하여 단일 가우시안 뿐만 아니라 복수 혼합 가우시안 모델이 함께 사용된다. 제안된 방법들을 이용하여 BN-96과 WSJ5k 데이터를 사용한 연속 음성 인식 실험을 수행한 결과, 표준 결정 트리를 사용한 시스템과 비교하여 공유 상태의 개수를 비슷하게 유지하면서 단어 오인식률을 줄일 수 있었다.