Earticle

음성 인식 성능 저하의 문제는 모델 훈련 환경과 인식 환경의 차이이다. 이러한 환경의 불일치를 줄이기 위 한 방법으로 다양한 묵음 특징 정규화 방법을 사용하고 있다. 기존의 묵음 특징 정규화 방법은 낮은 신호 대 잡음비 에서 묵음 구간의 에너지 레벨이 증가하여 음성과 비음성에 대한 분류의 정확도가 떨어짐으로 인해 인식 성능이 저 하되는 문제점이 있다. 본 논문에서는 음성 에너지 최대화와 묵음 특징 정규화를 이용한 잡음 환경에 강인한 음성 검 출 방법을 제안하였다. 제안한 방법은 높은 신호 대 잡음비에서는 음성 에너지를 최대화시켜 특징이 잡음의 영향을 적게 받는 특성을 이용하였고 낮은 신호 대 잡음비에서는 음성/비음성의 켑스트럼 특징 분포 특성을 이용하여 인식 성능을 향상시켰다. 인식 실험 결과 기존 방법에 비해 향상된 인식 성능을 확인할 수 있었다.

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for voice and non-voice classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a silence feature normalization and voice energy maximize. In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the voice energy. Cepstral feature distribution of voice / non-voice characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

음성 인식에서 기존의 음성 특징 추출 방법은 명확하지 않은 스레숄드 값으로 인해 부정확한 음성 인식률 을 가진다. 본 연구에서는 음성과 비음성에 대한 특징 추출을 묵음 특징 정규화를 융합한 음성 인식 성능 향상을 위한 방법을 모델링 한다. 제안한 방법에서는 잡음의 영향을 최소화하여 모델을 구성하였고, 각 음성 프레임에 대해 음성 신호 특징을 추출하여 음성 인식 모델을 구성하였고, 이를 묵음 특징 정규화를 융합하여 에너지 스펙트럼을 엔트로피와 유사하게 표현하여 원래의 음성 신호를 생성하고 음성의 특징이 잡음을 적게 받도록 하였다. 셉스트럼 에서 음성과 비음성 분류의 기준 값을 정하여 신호 대 잡음 비율이 낮은 신호에서 묵음 특징 정규화로 성능을 향상 하였다. 논문에서 제시하는 방법의 성능 분석은 HMM과 CHMM을 비교하여 결과를 보였으며, 기존의 HMM과 CHMM을 비교한 결과 음성 종속 단계에서는 2.1%p의 인식률 향상이 있었으며, 음성 독립 단계에서는 0.7%p 만큼 의 인식률 향상이 있었다.

Existing Speech feature extracting method in speech Signal, there are incorrect recognition rates due to incorrect speech which is not clear threshold value. In this article, the modeling method for improving speech recognition performance that combines the feature extraction for speech and silence characteristics normalized to the non-speech. The proposed method is minimized the noise affect, and speech recognition model are convergence of speech signal feature extraction to each speech frame and the silence feature normalization. Also, this method create the original speech signal with energy spectrum similar to entropy, therefore speech noise effects are to receive less of the noise. the performance values are improved in signal to noise ration by the silence feature normalization. We fixed speech and non speech classification standard value in cepstrum For th Performance analysis of the method presented in this paper is showed by comparing the results with CHMM HMM, the recognition rate was improved 2.7%p in the speech dependent and advanced 0.7%p in the speech independent.

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for speech and non-speech classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a SFN (silence feature normalization) and SEM (speech energy maximize). In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the speech energy. Cepstral feature distribution of speech and non-speech characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for speech and non-speech classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a SFN(silence feature normalization) and SEM(speech energy maximize). In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the speech energy. Cepstral feature distribution of speech and non-speech characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.