http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 정현열 (검색결과 94 건)
- 무료
- 기관 내 무료
- 유료
-
-
정현열,허성필 한국음향학회 2004 韓國音響學會誌 Vol.23 No.6
본고에서는 악곡정보 검색을 위한 검색키로써 허밍을 이용한 검색 방법에 관한 내용을 기술하였다. 고정도의 악곡 검색 시스템은 사용자의 불안정한 음정 및 템포 그리고 애매한 기억에 의한 음표의 삽입 및 탈락에 대응이 가능해야 한다. 또한 입력된 음향신호로부터 검색에 필요한 정확한 특징량의 추출과 효과적인 멜로디 표현 기법이 요구된다. 일반적으로 사용자의 허밍으로부터 음고 정보를 얻기 위해 입력된 음향신호로부터 피치정보를 추출하지만, 피치 추출 알고리즘은 이러한 입력 허밍으로부터 때때로 하모닉 피치를 추출한다. 이러한 문제점을 고려하여, 본 논문에서는 음고 정보의 특징량으로 복수 피치 후보를 고려한 방법을 제안한다. 게다가 복수 피치 후보에 신뢰도라는 파라미터를 도입하여 신뢰도가 높은 피치후보의 선택 가능성을 높였다. 검색엔진에서는 제안하는 복수 피치 후보의 수용을 위해 DP알고리즘을 3차원으로 확장하였다. 또한 제안하는 알고리즘은 DP패스에 따라 음표의 삽입/탈락에 다이내믹하게 대응이 가능하도록 멜로디 표현 방법을 변경하였다. 성능 평가를 위해 종래 기법과의 비교 실험 결과 보다 높은 검색 결과를 얻었다. This paper describes a music information retrieval system which uses humming as the key for retrieval Humming is an easy way for the user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is a human factor. Sometimes people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract pitch from the user's humming. However pitch extraction is not perfect. It often captures half or double pitches. even if the extraction algorithms take the continuity of the pitch into account. Considering these problems. we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates. the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of an algorithm with three dimensions that is an extension of the conventional DP algorithm, so that multiple pitch candidates can be treated. Moreover in the proposed algorithm. DP paths are changed dynamically to take deltaPitches and IOIratios of input and reference notes into account in order to treat notes being split or unified. We carried out an evaluation experiment to compare the proposed system with a conventional system. From the experiment. the proposed method gave better retrieval performance than the conventional system.
-
결정트리 상태 클러스터링에 의한 HM-Net 구조결정 알고리즘을 이용한 음성인식에 관한 연구
정현열,정호열,오세진,황철준,김범국 한국음향학회 2002 韓國音響學會誌 Vol.21 No.2
본 논문은 한국어 음성인식에서 음향모델의 성능개선을 위한 기초적 연구로서 결정트리 상태 클러스터링에 의한 HM-Net (Hidden Markov Network)의 구조결정 알고리즘을 이용한 음성인식에 관한 연구를 수행하였다. 한국어는 다른 언어와 비교하여 많은 문법과 변이음이 존재하는데, 국어 음성학에서 정의한 다양한 변이음을 조사하고, 음소결정트리를 위한 음소 질의어 집합을 작성하였다. 본 논문의 HM-Net 구조결정 알고리즘의 아이디어는 SSS (Successive State Splitting) 알고리즘의 구조를 가지면서 미리 작성해 둔 문맥의존 음향모델의 상태를 다시 분할하는 방법이다. 즉, 모델의 각 상태위치마다 음소 질의어 집합에 의해 음소결정트리를 생성하고, PDT-SSS (Phonetic Decision Tree-based SSS) 알고리즘에 의해 문맥의존 음향모델의 상태열을 다시 학습하는 방법이다. 결정트리 상태 클러스터링에 의한 HM-Net 구조결정 알고리즘의 유효성을 확인하기 위해, 국어공학센터 (KLE)의 452단어와 항공편 예약에 관련된 YNU200 문장을 대상으로 음성인식 실험을 수행하였다. 인식실험 결과, 음소, 단어, 연속음성인식 실험에서 상태분할을 수행한 후 상태수의 변화에 따라 인식률이 점진적으로 향상됨을 확인하였다. 상태수 2,000일 때 음소, 단어 인식률이 평균 71.5%, 99.2%를 각각 얻었으며, 연속음성인식률은 상태수 800일 때 평균 91.6%를 얻었다. 또한 HM-Net 구조결정 알고리즘의 파라미터 공유관계를 비교하기 위해 상태공유를 수행하는 HTK를 이용한 단어인식 실험을 수행하였다. 실험결과, HTK를 이용한 문맥의존 음향모델에 비해 평균 4.0%의 인식률 향상을 보여, 본 논문에서 적용한 결정트리 상태 클러스터링에 의한 HM-Net 구조결정 알고리즘의 유효성을 확인하였다. In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.
-
정현열,Nguyen, Dinh Cuong,Chung, Hyun-Yeol 한국음향학회 2010 韓國音響學會誌 Vol.29 No.e1
In this paper, we present the use of the Features Weighted Mahalanobis Distance (FWMD) in improving the performance of Likelihood Maximizing Beamforming (Limabeam) algorithm in speech recognition for microphone array. The proposed approach is based on the replacement of the traditional distance measure in a Gaussian classifier with adding weight for different features in the Mahalanobis distance according to their distances after the variance normalization. By using Features Weighted Mahalanobis Distance for Limabeam algorithm (FWMD-Limabeam), we obtained correct word recognition rate of 90.26% for calibrate Limabeam and 87.23% for unsupervised Limabeam, resulting in a higher rate of 3% and 6% respectively than those produced by the original Limabearn. By implementing a HM-Net speech recognition strategy alternatively, we could save memory and reduce computation complexity.
-
CCITT G.722 CODEC을 경유한 연속음성의 인식
정현열 嶺南大學校 工業技術硏究所 1995 工業技術硏究所論文集 Vol.23 No.1
To examine the robustness of ordinary continuous speech recognition system being applied to the speech transmitted via 64kbit/s(7㎑) transmission line, we consisted CODEC according to the CCITT Recommendation G.722 which regulates the transmission line, and compared the differences in recognition results. In the tests, we selected independently 1018 sentences for train and 140 sentences for test from the speech data by 150 speakers. The correct recognition rate of 85.6% was obtained with CODEC'ed speech, which was about 1% lower than 86.7% with directly uttered speech. The difference in two recognition rates was considered by BER (Bit Error Rate) in coding system included in CODEC.
-
-
-
최종룡,정현열 嶺南大學校 工業技術硏究所 1994 工業技術硏究所論文集 Vol.22 No.2
Multi-layered feed-forward neural networks(NN) are applied to the recognition of Korean initial stop consonants. The recognition results are then compared with those by Bayesian decision rule(BDR) to find out 1) the numbers of hidden layers and units of each layer which lead best recognition in the NN and 2) the differences of recognition trend in these two, 3) factors to cause recognition error. In the recognition by NN with one hidden layer, 100 units and 80ms of duration, the best recognition rate of 81.0% was obtained. Both NN and BDR showed that it is hard to distinguish lenes from tense and fortes caused by the confusion between the places of the same type of articulation.
-
-
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
