• 말소리와 음성과학
• /
• 제6권2호
• /
• pp.29-34
• /
• 2014

In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.

• 음성과학
• /
• 제13권2호
• /
• 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.

• 대한음성학회지:말소리
• /
• 제62호
• /
• pp.97-112
• /
• 2007

The speech recognizer in general operates in noisy acoustical environments. Many research works have been done to cope with the acoustical variations. Among them, the multiple-HMM model approach seems to be quite effective compared with the conventional methods. In this paper, we consider a multiple-model approach combined with the model compensation method and investigate the necessary number of the HMM model sets through noisy speech recognition experiments. By using the data-driven Jacobian adaptation for the model compensation, the multiple-model approach with only a few model sets for each noise type could achieve comparable results with the re-training method.

• 음성과학
• /
• 제11권2호
• /
• 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.

• 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.

• 한국전산유체공학회지
• /
• 제17권4호
• /
• pp.32-40
• /
• 2012

Efficient Global Optimization (EGO) method is a global optimization technique which can select the next sample point automatically by infill sampling criteria (ISC) and search for the global minimum with less samples than what the conventional global optimization method needs. ISC function consists of the predictor and mean square error (MSE) provided from the kriging model which is a stochastic metamodel. Also the constrained EGO method can minimize the objective function dealing with the constraints under EGO concept. In this study the constrained EGO method applied to the RAE2822 airfoil shape design formulated with the constraint. But the noisy CFD data caused the kriging model to fail to depict the true function. The distorted kriging model would make the EGO deviate from the correct search. This distortion of kriging model can be handled with the interpolation(p=free) kriging model. With the interpolation(p=free) kriging model, however, the search of EGO solution was stalled in the narrow feasible region without the chance to update the objective and constraint functions. Then the accuracy of EGO solution was not good enough. So the three-step search method was proposed to obtain the accurate global minimum as well as prevent from the distortion of kriging model for the noisy constrained CFD problem.

• 음성과학
• /
• 제14권2호
• /
• 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.

• 한국음향학회지
• /
• 제40권5호
• /
• pp.479-487
• /
• 2021

본 논문에서는 잡음 학생 모델 기반의 자가 학습을 활용한 음향 사건 검지 기법을 제안한다. 제안된 음향 사건 검지 모델은 두 단계로 구성된다. 첫 번째 단계에서는 잔차 합성곱 순환 신경망(Residual Convolutional Recurrent Neural Network, RCRNN)을 훈련하여 레이블이 지정되지 않은 비표기 데이터셋의 레이블 예측에 활용한다. 두 번째 단계에서는 세 가지 잡음 종류를 적용한 잡음 학생 모델을 자가학습 기법으로 반복하여 학습한다. 여기서 잡음 학생 모델은 SpecAugment, Mixup, 시간-주파수 이동을 활용한 특징 잡음, 드롭아웃을 활용한 모델 잡음, 그리고 semi-supervised loss function을 적용한 레이블 잡음을 활용하여 학습된다. 제안된 음향 사건 검지 모델의 성능은 Detection and Classification of Acoustic Scenes and Events(DCASE) 2020 Challenge Task 4의 validation set으로 평가하였다. DCASE 2020 챌린지 데이터셋의 baseline 및 최상위 랭크된 모델과 이벤트 단위 F1 점수 성능을 비교한 결과, 제안된 음향 사건 검지 모델이 단일 모델과 앙상블 모델에서 최상위 모델 대비 F1 점수를 각각 4.6 %와 3.4 % 향상시켰다.

• The Journal of the Acoustical Society of Korea
• /
• 제29권2E호
• /
• pp.100-106
• /
• 2010

Multiple-model speech recognizer has been shown to be quite successful in noisy speech recognition. However, its performance has usually been tested using the general speech front-ends which do not incorporate any noise adaptive algorithms. For the accurate evaluation of the effectiveness of the multiple-model frame in noisy speech recognition, we used the state-of-the-art front-ends and compared its performance with the well-known multi-style training method. In addition, we improved the multiple-model speech recognizer by employing N-best reference HMMs for interpolation and using multiple SNR levels for training each of the reference HMM.

• 한국음향학회지
• /
• 제20권2호
• /
• pp.21-26
• /
• 2001

본 논문에서는 잡음에 강인한 음성인식을 위해서 expectation-maximization (EM) 방식을 이용하여 잡음의 평균값을 추정하는 새로운 알고리듬을 제안하였다. 제안된 알고리듬에서는 온라인상의 인식용 음성이 직접 Bayesian 적응을 위해서 사용되며, 또한 훈련데이터를 이용하여 잡음의 평균값에 대한 사전 (prior) 분포를 알아낸 후 Bayesian 적응시에 이용한다. 잡음 음성의 모델링을 위해서는 PMC (parallel model combination) 방식을 이용하였고, 제안된 방식을 이용하여 자동차 잡음 환경 하에서 인식 실험을 수행한 결과, 기존의 PMC 방식에 비해서 향상된 인식성능을 보임을 알 수 있었다.