• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.33-36
• /
• 2004

최근 연속 음성 인식에서의 성능 향상을 위하여 음절을 인식 단위로 사용하고자 하는 노력들이 보고되고 있다. 그러나 음절의 경우 음소에 비해 학습성이 좋지 않고 모델의 수가 많으므로 음절 경계에서의 문맥 종속 모델링이 어렵다는 단점을 갖고 있다. 본 논문에서는 음절의 이러한 단점을 극복하기 위하여 모노폰과 트라이폰을 이용하여 음절 모델을 합성하는 방법을 제안한다. 제안된 모델은 트라이폰에 비하여 평균 $55\%$, PTM에 비하여 평균 $13\%$의 인식 속도 향상을 보이며, 동일한 속도일 경우 PTM, 트라이폰 모델 모두에 대하여 ERR이 약$8\%$ 향상됨을 볼 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.96-100
• /
• 2006

Kim et al. Proposed Normalized Confidence Measure (NCM) [1-2] and it was successfully used for rejecting mis-recognized words in isolated word recognition. However their experiments were performed on the fixed word speech recognition. In this Paper we apply NCM to the domain of vocabulary independent speech recognition (VISP) and shows the rejection Performance of NCM in VISP. Specialty we Propose vector quantization (VQ) based method for overcoming the problem of unseen triphones. It is because NCM uses the statistics of triphone confidence in the case of triphone-based normalization. According to speech recognition experiments Phone-based normalization method shows better results than RLJC[3] and also triphone-based normalization approach. This results are different with those of Kim et al [1-2]. Concludingly the Phone-based normalization shows robust Performance in VISP domain.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.6
• /
• pp.867-874
• /
• 2001

In this paper, considering the pronunciation characteristic of Korean, recognition units which can shorten the recognition time and reflect the coarticulation effect simultaneously are suggested. These units are composed of monophone and hipbone ones. Monophone units are applied to the vowels which represent stable characteristic. Biphones are used to the consonant which vary according to adjacent vowel. In the experiment of word recognition of PBW445 database, the compound units result in comparable recognition accuracy with 57％ speed up compared with triphone units and better recognition accuracy with similar speed. In addition, we can reduce the memory size because of fewer units.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.5
• /
• pp.747-754
• /
• 2004

In this paper, we obtain an optimal corpus that can represent its characteristics very well from the baseline corpus which consists of unique 1,566,943 names among company names in a directory assistance serve (114). Two kinds of optimal solutions ared considered to obtain the optimal corpus. The first solution is to find phonetically balanced corpus (PBC), which are the minimum set including all possible triphones in the baseline corpus. The second solution is to find the phonetically distributed corpus (PDC), which is a minimum set representing the frequency characteristics of triphones in the baseline corpus. We can obtain 8,699 words as the PBC and 16,783 words (similarity measure R = 0.92) as PDC, respectively. These corpora can be used for the development of speech recognition and speech synthesis.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.572-577
• /
• 2009

Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. To prune the redundant speech segments in a large speech segment DB, we can utilize a decision-tree based triphone clustering algorithm widely used in speech recognition area. But, the conventional methods have problems in representing the acoustic transitional characteristics of the phones and in applying context questions with hierarchic priority. In this paper, we propose a new clustering algorithm to downsize the speech DB. Firstly, three 13th order MFCC vectors from first, medial, and final frame of a phone are combined into a 39 dimensional vector to represent the transitional characteristics of a phone. And then the hierarchically grouped three question sets are used to construct the triphone trees. For the performance test, we used DTW algorithm to calculate the acoustic similarity between the target triphone and the triphone from the tree search result. Experimental results show that the proposed method can reduce the size of speech DB by 23% and select better phones with higher acoustic similarity. Therefore the proposed method can be applied to make a small sized TTS.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.93-96
• /
• 2004

본 논문은 TMS320C5501 16bit DSP를 적용한 실시간 화자독립 연속 숫자인식기의 구현에 관해 서술한다. 하드웨어 모듈의 구성은 TMS320C5501 300MHz DSP, 코덱으로는 TLV320AIC1103, SDRAM, 외부장치와의 인터페이스를 위한 HPI, Uart, MIC, SPK Out 단자로 구성되었다. 음성인식 알고리즘은 HM-Net 방식을 사용하였고 고정소수점 연산처리 방식으로 C를 이용한 최적화 작업을 수행하였으며 스트리밍 방식의 인식 방법으로 실시간 처리가 가능하도록 구현하였다. 숫자 인식에 사용한 모델은 41음소에 기반한 트라이폰을 학습하였으며, 특징 파라미터로는 LPCMEL 20차를 사용하였다. 임베디드 시스템의 실시간 음성인식 시스템 구성에 중점을 두었으며 PC상에서의 성능과 비교해 볼때 본 DSP 상에서 500단어, 50문장의 인식을 평균 1.5초 전후로 인식하도록 하였으며 간단한 연결 단어 인식을 수행하는데 무리 없음을 보여준다. 특별히 한국어 연속숫자 부분에 중점을 두었고, 본 연구에서 구현된 연속 음성인식 시스템에 사용된 숫자 인식에서 음절 바이폰 모델에 대하여 $92.92\%$의 인식율을 얻을 수 있었다.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.41-44
• /
• 2006

The purpose of state tying is to reduce the number of models and to use relatively reliable output probability distributions. There are two approaches: one is top down clustering and the other is bottom up clustering. For seen data, the performance of bottom up approach is better than that of top down approach. In this paper, we propose a new clustering technique that can enhance the undertrained triphone clustering performance. The basic idea is to tie unreliable triphones before clustering. An unreliable triphone is the one that appears in the training data too infrequently to train the model accurately. We propose to use monophone distance to preprocess these unreliable triphones. It has been shown in a pilot experiment that the proposed method reduces the error rate significantly.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.110-113
• /
• 2011

스마트 폰의 보급이 대중화됨에 따라 다양한 앱들이 사용되고 있으나 효율적인 사전 탐색에 관한 앱은 그다지 많지 않다. 현재 공개된 한국어 사전 탐색 앱은 완전한 단어이거나 단어의 부분 문자열을 질의로 사용한다. 이 경우 완전한 단어를 기억하지 못하거나 한국어 정보처리를 위한 여러 형태의 음운 정보를 쉽게 탐색할 수 없다. 이러한 문제를 개선하기 위해 본 논문에서는 메타문자를 사용하여 효율적으로 단어를 탐색할 수 있는 앱을 개발한다. 본 논문에서 사용하는 메타문자는 임의의 음절을 표현하는 '*'와 '?'과 종성을 표현하는 ':'를 사용하며 사전구조는 자소 단위의 트라이를 사용한다. 또한 음절은 물론이고 자소(초성, 중성, 종성)로 구성된 질의를 탐색할 수 있다. 더구나 음절과 자소가 혼합된 질의도 사용할 수 있도록 하여 사용자의 편의를 크게 도모하였다.

• Tribology and Lubricants
• /
• v.29 no.3
• /
• pp.167-170
• /
• 2013

The friction behavior of human skin is determined by the complex interplay of the material and surface properties of the skin, as well as the contacting material, and strongly depends on the contact parameters (e.g., pressure and sliding velocity) and the presence of substances such as water, sweat, or skin surface lipids at the interface. Including a study on the effect of a surface's physical roughness for skin sliding over the surface, various studies have been conducted to understand human tactile sensibility. However, to investigate products in relation to human tactile sensibility, more objective research is needed. This study performed sliding experiments between the skin and the surfaces of phone cases to understand how the texture, friction, and stick-slip characteristics are related. Eight phone case surfaces with different topologies and chemical (or mechanical) compatibilities with skin were prepared and tested multiple times.

• MALSORI
• /
• no.43
• /
• pp.57-72
• /
• 2002

The technology of speech recognition has a wide field of application. The range of such technology is spreading into mobile computing having the large amount of movement for communication equipments at the present time. Particularly, recognition in internet environment is rapidly moving into mobile environment. Because of these environments, users want the faster speed of data transmission and the lighter portable equipment for data access. That is PDA(Personal Digital Assistant). Therefore, we designed a triphone-based text independent vocabulary recognizer for the implementation of speech control in this paper. The text independent vocabulary recognizer is based on the state .joint algorithm with decision trees