• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.430-437
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.75-80
• /
• 2010

Noise handing is very important in voice recognition of vehicle environment. that has been studying about to hardware and software approach. hardware method that is noise filter circuit design, basically using Low-pass filter. it was shown a good result. and the side of software that has been developing about to algorithm for Noise canceler, NN(neural network), etc. in this paper we have analysis about to classified parameter pattern matting level for voice recognition on car noise environment that use of DTW(Dynamic Time Warping) which is applicable time series pattern recognition algorithm.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.115-122
• /
• 1999

In this paper, we confirmed that a speech signal is a chaos signal, and in order to use it as a speaker recognition parameter, analyzed chaos dimension. In order to raise speaker identification and pattern recognition, by making up the strange attractor involving an individual's vocal tract characteristics very well and applying fuzzy membership function to correlation dimension, we proposed fuzzy correlation dimension. By estimating the correlation of the points making up an attractor are limited according space dimension value, fuzzy correlation dimension absorbed the variation of the reference pattern attractor and test pattern attractor. Concerning fuzzy correlation dimension, by estimating the distance according to the average value of discrimination error per each speaker and reference pattern, investigated the validity of speaker recognition parameter.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.12
• /
• pp.1324-1335
• /
• 1991

In this paper, a phoneme separation and an establishment of discriminative pattern of Korean phonemes are studied on experiment. The separation uses parameters such as pitch extraction, glottal peak pulse width of each pitch. speech duration. envelope and amplitude bias. The first pitch is extracted by deviations of glottal peak and width. energy and normalization on a bias on the top of vowel envelope. And then, it traces adjacent pitch to vowel in whole. On vewel, amethod to be reduced gliding pattern and the possible of vowel distinction to be used just second formant are proposed, and shrinking pitch waveform has nothing to do with pitch length is estimated. A pattern of envelope, spectrum, shrinking waveform, and a method of analysis by mutual relation among phonemes and manners of articulation on consonant are detected. As experimental results, 90% on vowel phoneme, 80% and 60% on initial and final consonant are discriminated.

• The Magazine of the IEIE
• /
• v.15 no.2
• /
• pp.75-87
• /
• 1988

본 논문에서는 음성에 의한 man-machine communication의 핵심기술인 음성인식 및 합성의 전반적인 기술에 관하여 그 현황을 알아본다. 먼저 음성인식에서 해결되어야 할 문제점들을 고찰하고 격리단어 인식, 연결단어 인식, 그리고 연속언어 인식의 기술현황을 기술한다. 격리단어 인식에서는 pattern matching 방법에서 사용되는 입력어휘의 특징 추출, reference와의 유사도 측정, 유사도 측정 결과에 의한 인식결정에 관해서 논한다. 연결단어 및 연속언어 인식에서는 현재 연구가 되고 있는 "bottom-up approach"와 "top-down approach"에 관해서 설명하고 이들 방법의 어려운 점들을 고찰한다. 다음 음성 합성에서는 기존의 여러 가지 합성 방식을 검토하고 이들의 장단점을 기술한다. 마지막으로 한 예로서 한국어 text-to-speech 변환 시스템에 관하여 기술한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1985.10a
• /
• pp.59-63
• /
• 1985

불특정 화자의 음성인식을 위해 150 숫자음에 대하여 10개의 표준패턴을 설정하는데 목적을 두고 기술했다. 남성화자 3인이 각숫자음(0-9)를 5번씩 반복 발음한 150음을 지단화하여 숫자음의 표준패턴을 설정하였다. 특징 파라미터는 포르만트 주파수를 이용하였고 유크리드 거리 측정법을 유사도 비교에 사용하였다. 실험결과 85.3%의 인식률을 얻었다.

• MALSORI
• /
• no.33_34
• /
• pp.137-148
• /
• 1997

이 논문의 목적은 표준한국어의 강세유형을 Hayes(1995)의 Metrical Stress Theory의 틀내에서 형식화하는 것이다. 표준한국어의 강세 유형에 대해서는 여러 가지 설이 있으나 이 논문에서는 이 현복(1989)의 기술을 분석대상으로 삼았다. 이 현복(1989)에 따르면 한국어의 강세는 단어의 첫 두 음절 중 하나에 온다. 첫 음절이 중음절이면 그 음절에 강세가 오며 그 외의 경우에는 두번째 음절에 강세가 온다. 이와 같은 강세 규칙을 footing의 존재 여부, footing의 반복성, 그리고 footing의 방향을 고려하여 살펴보면 표준한국어의 강세 유형은 "왼쪽 끝에서 시작되는 비반복 footing을 보이는 iamb"이다.

• MALSORI
• /
• no.40
• /
• pp.51-63
• /
• 2000

There are sentences where sentence stress is imposed on a specific word. These sentences are called 'focused sentences'. The purpose of this paper is to investigate the variation of pitch, duration, amplitude in focused words. It is noted that pitch of a focused word is higher than that of unfocused words irrespective of the accentual pattern, and that contour tones such as HL or LH are realized longer when these tones appear in focused words. Not only the noun but also the following particle like '-boda' is higher when these words are in focus. Hence pitch is proved to be the most salient prosodic feature of the focused sentence.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.681-682
• /
• 2016

본 논문에서는 화자 식별에서 음성신호의 애매한 점을 보완할 수 있는 신경회로망의 오차역전파학습 알고리즘과 모음구간 검출에 기초하여 입력되는 음성의 화자 패턴을 구분하는 일본어 단어 패턴인식 알고리즘을 제안한다. 제안하는 알고리즘에서는 일본어 데이터베이스로부터의 단어를 사용하여 음성의 특징벡터를 추출하여 분석하고 이러한 음성의 특징벡터의 차이를 이용하여 일본어 화자에 대한 패턴인식 실험을 수행하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.1
• /
• pp.95-112
• /
• 1998

The Error Backpropagation algorithm is widely used in various areas such as associative memory, speech recognition, pattern recognition, robotics and so on. However, if and when a new leaning pattern has to be added in order to drill, it will have to accomplish a new learning with all previous learning pattern and added pattern from the very beginning. Somehow, it brings about a result which is that the more it increases the number of pattern, the longer it geometrically progress the time required by leaning. Therefore, a so-called Incremental Learning Method has to be solved the point at issue all by means in case of situation which is periodically and additionally learned by numerous data. In this study, not only the existing neural network construction is still remained, but it also suggests a method which means executing through added leaning by a model pattern. Eventually, for a efficiency of suggested technique, both Monk's data and Iris data are applied to make use of benchmark on machine learning field.