A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize...A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.展开更多
The double-peak characteristic of underwater radiated noise in the near field on top of the target submarine was analyzed in depth on the basis of submarine test data on the sea. The contribution of three major noise ...The double-peak characteristic of underwater radiated noise in the near field on top of the target submarine was analyzed in depth on the basis of submarine test data on the sea. The contribution of three major noise sources to the radiated noise of a submarine were compared and analyzed, and emphasis was put on the original source, production mechanism, and their correlative characteristics. On the basis of analysis on underwater tracking and pass through characteristics of the target submarine, the double-peak phenomenon was reasonably interpreted. Furthermore, the correctness of the theoretical interpretation was verified adequately in real submarine tests. The double-peak phenomenon indicates that the space distributing character on submarine radiated noise are both asymmetrical with time and space, whereas that is provided with directivity. Studying the double-peak phenomenon in depth has important reference value and meaning in engineering practice for understanding the underwater radiated noise field of submarines.展开更多
When the underexpanded supersonic jet impinges on the obstacle, it is well known that the self-induced flow os- cillation occurs. This oscillation depends on the pressure ratio in the flowfield, the position of an obs...When the underexpanded supersonic jet impinges on the obstacle, it is well known that the self-induced flow os- cillation occurs. This oscillation depends on the pressure ratio in the flowfield, the position of an obstacle and is related with the noise problems of aeronautical and other industrial engineering. The characteristic and the mechanism of self-induced flow oscillation, have to be clarified to control various noise problems. But, it seems that the characteristics of the oscillated flowfield and the mechanism of an oscillation have to be more cleared to control the oscillation. This paper aims to clarify the effect of the pressure ratio and the obstacle position and the mechanism of self-induced flow oscillation by numerical analysis and experiment, when the underexpanded su- personic jet impinges on the cylindrical body. From the result of this study, it is clear that occurrence of the self-induced flow osciUation depends on the pressure balance in the flowfield.展开更多
基金The National Natural Science Foundation of China (No.61231002,61273266,51075068,60872073,60975017, 61003131)the Ph.D.Programs Foundation of the Ministry of Education of China(No.20110092130004)+1 种基金the Science Foundation for Young Talents in the Educational Committee of Anhui Province(No. 2010SQRL018)the 211 Project of Anhui University(No.2009QN027B)
文摘A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.
基金Supported by the Navy Equipment Advanced Research Project under Grant No. 40113070203
文摘The double-peak characteristic of underwater radiated noise in the near field on top of the target submarine was analyzed in depth on the basis of submarine test data on the sea. The contribution of three major noise sources to the radiated noise of a submarine were compared and analyzed, and emphasis was put on the original source, production mechanism, and their correlative characteristics. On the basis of analysis on underwater tracking and pass through characteristics of the target submarine, the double-peak phenomenon was reasonably interpreted. Furthermore, the correctness of the theoretical interpretation was verified adequately in real submarine tests. The double-peak phenomenon indicates that the space distributing character on submarine radiated noise are both asymmetrical with time and space, whereas that is provided with directivity. Studying the double-peak phenomenon in depth has important reference value and meaning in engineering practice for understanding the underwater radiated noise field of submarines.
文摘When the underexpanded supersonic jet impinges on the obstacle, it is well known that the self-induced flow os- cillation occurs. This oscillation depends on the pressure ratio in the flowfield, the position of an obstacle and is related with the noise problems of aeronautical and other industrial engineering. The characteristic and the mechanism of self-induced flow oscillation, have to be clarified to control various noise problems. But, it seems that the characteristics of the oscillated flowfield and the mechanism of an oscillation have to be more cleared to control the oscillation. This paper aims to clarify the effect of the pressure ratio and the obstacle position and the mechanism of self-induced flow oscillation by numerical analysis and experiment, when the underexpanded su- personic jet impinges on the cylindrical body. From the result of this study, it is clear that occurrence of the self-induced flow osciUation depends on the pressure balance in the flowfield.
