• The Journal of the Acoustical Society of Korea
• /
• v.27 no.4
• /
• pp.191-199
• /
• 2008

In this paper, we propose a MWF-PMC noise processing method which enhances the input speech by using Mel-warped Wiener Filtering (MWF) at pre-processing stage and compensates the recognition model by using PMC (Parallel Model Combination) at post-processing stage for speech recognition in noisy environments. The PMC uses the residual noise extracted from the silence region of enhanced speech at pre-processing stage to compensate the clean speech model and thus this method is considered to improve the performance of speech recognition in noisy environments. For recognition experiments we dew.-sampled KLE PBW (Phoneme Balanced Words) 452 word speech data to 8kHz and made 5 different SNR levels of noisy speech, i.e., 0dB. 5dB, 10dB, 15dB and 20dB, by adding Subway, Car and Exhibition noise to clean speech. From the recognition results, we could confirm the effectiveness of the proposed MWF-PMC method by obtaining the improved recognition performances over all compared with the existing combined methods.

• Journal of Information Technology Application
• /
• v.1 no.3_4
• /
• pp.69-90
• /
• 1999

본 논문은 시계열자료의 ARMA 모형화를 위해 계층적(Hierarchical) 문제해결 방식인 인공신경망 기초 의상결정트리분류기상의 인공신경망 구조를 개선하여 지역문제(Local Problem)를 해결하는 복수개의 인공신경망 결과를 Dempster's rule of combination을 이용하여 종합하는 병행적인 (Parallel) ARMA 모형활르 위한 방법론을 제시함으로써 의사결정트리분류기에 근거한 방법론의 단점을 보완하였다. 본 논문에서 제시한 ARMA 모형화를 위한 방법론은 세 단계로 구성되어 있다: 1) ESACF 특성 벡터 추출단계; 2) 개별 인공신경망에 의한 부분적 모델링 단계; 3) Conflict Resolution 단계, 제시한 방법론을 검증하기 위해 모의실험용 자료와 실제 시계열자료를 이용하여 제시된 방법론을 검증하였으며 실험결과 기존 연구에 비해 ARMA 모형화와 정확도가 높은 것으로 나타났다.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.247-257
• /
• 2004

There has been many research efforts to overcome the problems of speech recognition in the noisy conditions. Among them, the model-based compensation methods such as the parallel model combination (PMC) and vector Taylor series (VTS) have been found to perform efficiently compared with the previous speech enhancement methods or the feature-based approaches. In this paper, a data-driven model compensation approach that adapts the HMM(hidden Markv model) parameters for the noisy speech recognition is proposed. Instead of assuming some statistical approximations as in the conventional model-based methods such as the PMC, the statistics necessary for the HMM parameter adaptation is directly estimated by using the Baum-Welch algorithm. The proposed method has shown improved results compared with the PMC for the noisy speech recognition.

• Speech Sciences
• /
• v.14 no.2
• /
• pp.115-126
• /
• 2007

There have been many research efforts to improve the performance of the speech recognizer in noisy conditions. Among them, the model compensation method and the speech enhancement approach have been used widely. In this paper, we propose to combine the two different approaches to further enhance the recognition rates in the noisy speech recognition. For the speech enhancement, the minimum mean square error-short time spectral amplitude (MMSE-STSA) has been adopted and the parallel model combination (PMC) and Jacobian adaptation (JA) have been used as the model compensation approaches. From the experimental results, we could find that the hybrid approach that applies the model compensation methods to the enhanced speech produce better results than just using only one of the two approaches.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1161-1164
• /
• 1998

We designed a DSP core simulator with C language, that is able to simulate 5-stage pipelined DSP core, named YS-DSP. It can emulate all 5 stage pipelines in the DSP core. It can also emulate memory access, exception processing, and DSP parallel processing. Each pipeline stage is implemented by combination of one or more functions to process parts of each stage. After modeling and validating the simulator, we can use it to verify and to complement the DSP core HDL model and to enhance its performance.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.1
• /
• pp.49-54
• /
• 1998

본 논문에서는 잡음이 존재하는 환경에 강인한 것으로 알려져 있는 투영 방법을 우 도 측정에 가중 함수와 결합하여 사용하는 방법을 제안하였다. 반연속 HMM을 이용한 고립 단어의 인식 실험 결과, 제안한 방법이 실험에 사용된 잡음의 환경들에서 모두 좋은 성능을 나타내었다. 아울러 병렬 모델 결합 방법을 반연속 HMM에 적용하였는데 이는 코드북의 변 환반으로 쉽게 잡음의 특성을 반영할 수 있다. 가중 투영 우도 측정 방법을 병렬 모델 결합 방법에 적용한 경우에도 우수한 성능을 거둘 수 있었다.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.75-84
• /
• 2006

Various methods have been proposed to overcome the problem of speech recognition in the noisy conditions. Among them, the model compensation methods like the parallel model combination (PMC) and Jacobian adaptation (JA) have been found to perform efficiently. The JA is quite effective when we have hidden Markov models (HMMs) already trained in a similar condition as the target environment. In a previous work, we have proposed an improved method for the JA to make it more robust against the changing environments in recognition. In this paper, we further improved its performance by compensating the delta-mean vectors and covariance matrices of the HMM and investigated its feasibility in the multi-model structure for the noisy speech recognition. From the experimental results, we could find that the proposed improved the robustness of the JA and the multi-model approach could be a viable solution in the noisy speech recognition.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.251-261
• /
• 2003

There has been many research efforts to overcome the problems of speech recognition in noisy conditions. Among the noise-robust speech recognition methods, model-based adaptation approaches have been shown quite effective. Particularly, the PMC (parallel model combination) method is very popular and has been shown to give considerably improved recognition results compared with the conventional methods. In this paper, we experimented with the VTS (vector Taylor series) algorithm which is also based on the model parameter transformation but has not attracted much interests of the researchers in this area. To verify the effectiveness of it, we employed the algorithm in the continuous density HMM (Hidden Markov Model). We compared the performance of the VTS algorithm with the PMC method and could see that the it gave better results than the PMC method.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 1997.10a
• /
• pp.159-166
• /
• 1997

The purpose of this thesis is to derive a theoretical model of the hysteretic resistance of the visco-elastic damper based on test results of harmonic excitation and to investigate of the basis of theory and experiment the effect of vibration control and response characteristics of portal frames degree vibration systems provided with the damper. The behaviour of a visco-elastic degree under dynamic loading is idealized by a model of the theory of visco-elasticity, i.e. a four-parameter model formed as a parallel combination of Maxwell fluid and Kelvin-Voigh models and its constitutive equation is derived. The model parameters are determined for a tested damper from the datas of harmonic excitation tests. The theoretical model of the damper is incorporated in equation fo motion of single degree of freedom. A computer program for solving the equation is written using Runge-kuttas's numerical integration scheme. Using this analysis program test cases of the earthquake excitation are simulated and the results of the simulation are the results of the simulation are the results of the simulation are compared with the test results.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.215-218
• /
• 2003

In this paper we apply PMC (parallel model combination) to speech recognition system online. As a representative of model based noise compensation techniques, PMC compensates environmental mismatch by combining pretrained clean speech models and real-time estimated noise information. This is very effective approach for compensating extreme environmental mismatch but is inadequate to use in on-line system for heavy computational cost. To reduce the computational cost and to apply PMC online, we use a noise masking effect - the energy in a frequency band is dominated either by clean speech energy or by noise energy - in the process of model compensation. Experiments on artificially produced noisy speech data confirm that the proposed technique is fast and effective for the on-line model compensation.