• 한국음향학회지
• /
• 제24권8호
• /
• pp.498-504
• /
• 2005

교육 및 연구 목적을 위하여 개발된 한국어 음성인식 플랫폼인 ECHOS를 소개한다. 음성인식을 위한 기본 모듈을 제공하는 BCHOS는 이해하기 쉽고 간단한 객체지향 구조를 가지며, 표준 템플릿 라이브러리 (STL)를 이용한 C++ 언어로 구현되었다. 입력은 8또는 16 kHz로 샘플링된 디지털 음성 데이터이며. 출력은 1-beat 인식결과, N-best 인식결과 및 word graph이다. ECHOS는 MFCC와 PLP 특징추출, HMM에 기반한 음향모델, n-gram 언어모델, 유한상태망 (FSN)과 렉시컬트리를 지원하는 탐색알고리듬으로 구성되며, 고립단어인식으로부터 대어휘 연속음성인식에 이르는 다양한 태스크를 처리할 수 있다. 플랫폼의 동작을 검증하기 위하여 ECHOS와 hidden Markov model toolkit (HTK)의 성능을 비교한다. ECHOS는 FSN 명령어 인식 태스크에서 HTK와 거의 비슷한 인식률을 나타내고 인식시간은 객체지향 구현 때문에 약 2배 정도 증가한다. 8000단어 연속음성인식에서는 HTK와 달리 렉시컬트리 탐색 알고리듬을 사용함으로써 단어오류율은 $40\%$ 증가하나 인식시간은 0.5배로 감소한다.

• Journal of Computing Science and Engineering
• /
• 제2권1호
• /
• pp.1-25
• /
• 2008

Spoken dialog tasks incur many errors including speech recognition errors, understanding errors, and even dialog management errors. These errors create a big gap between the user's intention and the system's understanding, which eventually results in a misinterpretation. To fill in the gap, people in human-to-human dialogs try to clarify the major causes of the misunderstanding to selectively correct them. This paper presents a method of clarification techniques to human-to-machine spoken dialog systems. We viewed the clarification dialog as a two-step problem-Belief confirmation and Clarification strategy establishment. To confirm the belief, we organized the clarification process into three systematic phases. In the belief confirmation phase, we consider the overall dialog system's processes including speech recognition, language understanding and semantic slot and value pairs for clarification dialog management. A clarification expert is developed for establishing clarification dialog strategy. In addition, we proposed a new design of plugging clarification dialog module in a given expert based dialog system. The experiment results demonstrate that the error verifiers effectively catch the word and utterance-level semantic errors and the clarification experts actually increase the dialog success rate and the dialog efficiency.

• 한국통신학회논문지
• /
• 제38C권3호
• /
• pp.303-310
• /
• 2013

수중에서의 통신은 해수면과 해저면 등에 의한 신호의 반사가 생겨 다중경로 현상이 발생한다. 이러한 다중경로의 영향으로 신호는 왜곡되고 원활한 수신을 방해하게 된다. 이러한 다중 경로 환경에서 본 논문에서는 수신신호의 성능을 향상시키고자 수중통신에 적합한 반복부호를 설정하였다. 적용가능한 반복부호로는 터보 부호와 LDPC 부호가 있으며, 성능 및 부호화 길이, 등화기 적용 등의 파라메타를 기반으로 수중통신에서는 터보 부호의 적용이 적합하다는 결론을 얻었다. 따라서 터보 부호 기반의 터보 등화기를 사용하여 실제 동해 바다에서 송수신 거리가 5Km 그리고 데이터 속도를 1Kbps로 설정하여 성능을 확인하였다.

• 한국통신학회논문지
• /
• 제31권9C호
• /
• pp.853-858
• /
• 2006

음성인식에서 TMHMM(Tied Mixture Hidden Markov Model)은 자유 매개변수의 수를 감소시키기 위한 좋은 접근이지만, GPDF(Gaussian Probability Density Function) 군집화 오류에 의해 음성인식의 오류를 발생시켰다. 본 논문은 TMHMM에서 발생하는 군집화 오류를 최소화하기 위하여 HCNN(Homogeneous Centroid Neural Network) 군집화 알고리즘을 제안한다. 제안된 알고리즘은 CNN(Centroid Neural Network)을 TMHMM상의 음향 특징벡터에 활용하였으며, 다른 상태에 소속된 확률밀도가 서로 겹쳐진 형태의 이질군집 지역에 더 많은 코드벡터를 할당하기 위해서 본 논문에서 새로 제안이 제안되는 이질성 거리척도를 사용 하였다. 제안된 알고리즘을 한국어 고립 숫자단어의 인식문제에 적용한 결과, 기존 K-means 알고리즘이나 CNN보다 각각 14.63%, 9,39%의 오인식률의 감소를 얻을 수 있었다.

• 말소리와 음성과학
• /
• 제10권1호
• /
• pp.49-55
• /
• 2018

This paper aims to describe a knowledge-based pronunciation generation system for French. It has been reported that a rule-based pronunciation generation system outperforms most of the data-driven ones for French; however, only a few related studies are available due to existing language barriers. We provide basic information about the French language from the point of view of the relationship between orthography and pronunciation, and then describe our knowledge-based pronunciation generation system, which consists of morphological analysis, Part-of-Speech (POS) tagging, grapheme-to-phoneme generation, and phone-to-phone generation. The evaluation results show that the word error rate of POS tagging, based on a sample of 1,000 sentences, is 10.70% and that of phoneme generation, using 130,883 entries, is 2.70%. This study is expected to contribute to the development and evaluation of speech synthesis or speech recognition systems for French.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1352-1355
• /
• 1987

This Paper proposed the modified binary n-gram algorithm for the contextual post processing system in English sentence. Backward gram was used to correct the first position error in a word. It is not requires additional storage but more times of comparison it allows interactive correction routine. Experiments were implemented using PASCAL language on a micro computer, IBM PC/XT. This algorithm improves the correction rate around $4{\sim}5%$ on a limited experimental environments.

• Journal of Communications and Networks
• /
• 제10권2호
• /
• pp.156-162
• /
• 2008

Cooperative relays can provide spatial diversity and improve performance of wireless communications. In this paper, we study subcarrier power allocation at the relays for orthogonal frequency division multiplexing (OFDM)-based wireless systems. For cooperative relay with amplify-and-forward (AF) and decode-and-forward (DF) algorithms, we investigate the impact of power allocation to the mutual information between the source and destination. From our simulation results on word~error-rate (WER) performance, we find that the DF algorithm with power allocation provides better performance than that of AF algorithm in a single path relay network because the former is able to eliminate channel noise at each relay. For the multiple path relay network, however, the network structure is already resistant to noise and channel distortion, and AF approach is a more attractive choice due to its lower complexity.

• 융합신호처리학회논문지
• /
• 제15권2호
• /
• pp.37-41
• /
• 2014

The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

• 음성과학
• /
• 제10권3호
• /
• pp.263-277
• /
• 2003

One of major problems in speech recognition is performance degradation due to the mismatch between the training and test environments. Recently, Stereo-based Piecewise LInear Compensation for Environments (SPLICE), which is frame-based bias removal algorithm for cepstral enhancement using stereo training data and noisy speech model as a mixture of Gaussians, was proposed and showed good performance in noisy environments. In this paper, we propose several methods to improve the conventional SPLICE. First we apply Cepstral Mean Subtraction (CMS) as a preprocessor to SPLICE, instead of applying it as a postprocessor. Secondly, to compensate residual distortion after SPLICE processing, two-stage SPLICE is proposed. Thirdly we employ phonetic information for training SPLICE model. According to experiments on the Aurora 2 database, proposed method outperformed the conventional SPLICE and we achieved a 50% decrease in word error rate over the Aurora baseline system.

• 한국음향학회지
• /
• 제18권6호
• /
• pp.57-64
• /
• 1999

본 논문에서는 잡음이 포함된 음성의 시작점과 끝점을 효율적으로 검출할 수 있는 알고리듬에 대하여 연구하였다. 이를 위해, 웨이브렛 영역에서의 에너지 분포를 고려함으로써 잡음환경하에서도 음성을 검출할 수 있는 새로운 검출 파라미터를 제안하였다. 제안된 끝점검출 파라미터는 웨이브렛 영역에서 세 번째 coarsed 스케일의 표준편차와 가중치를 곱한 첫 번째 detailed 스케일의 표준편차의 합으로 정의하였다. 제안된 끝점검출기의 성능평가를 위해서 다양한 SNR에서 기존방식과 비교하여 시작점과 끝점의 정확도 실험을 수행하였고 HMM 음성인식시스템을 이용하여 인식실험도 수행하였다.