Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration t...Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration technique of tone models into a large vocabulary continuous speech recognition system is presented. Discriminative model weight training based on minimum phone error criteria is adopted aiming at optimal integration of the tone models. The extended Baum Welch algorithm is applied to find the model-dependent weights to scale the acoustic scores and tone scores. Experimental results show that tone recognition rates and continuous speech recognition accuracy can be improved by the discriminatively trained tone model. Performance of a large vocabulary continuous Mandarin speech recognition system can be further enhanced by the discriminatively trained weight combinations due to a better interpolation of the given models.展开更多
Mercury sphygmomanometer (MSM) is reliable and widely used in clinics and hospitals. The principle of Korotkoff sounds method (KSM) applied in the MSM is also a gold standard to measure blood pressure. Many efforts ha...Mercury sphygmomanometer (MSM) is reliable and widely used in clinics and hospitals. The principle of Korotkoff sounds method (KSM) applied in the MSM is also a gold standard to measure blood pressure. Many efforts have been made attempting to replace MSM, which is criticized for being not healthy and safe. In this research, an electronic blood pressure monitor, named K-sounds electronic sphygmomanometer (KESM), was designed as a substitute to MSM. The three key elements of KSM were proposed for the first time. We used appropriate electronic components to build the KESM which can fulfill the functions related to the three key elements. The KESM, which was easy to operate and free of mercury, followed the same principle as MSM. The same principle guaranteed the comparable accuracy. We took equivalence test and the results showed that the designed KESM was as accurate as the calibrated standard MSM. The designed KESM passed the certifications of SFDA and is qualified in clinics or hospitals for diagnostic purposes.展开更多
Based on an auditory model, the zero-crossings with maximal Teager energy operator (ZCMT) feature extraction approach was described, and then applied to speech and emotion recognition. Three kinds of experiments were ...Based on an auditory model, the zero-crossings with maximal Teager energy operator (ZCMT) feature extraction approach was described, and then applied to speech and emotion recognition. Three kinds of experiments were carried out. The first kind consists of isolated word recognition experiments in neutral (non-emotional) speech. The results show that the ZCMT approach effectively improves the recognition accuracy by 3.47% in average compared with the Teager energy operator (TEO). Thus, ZCMT feature can be considered as a noise-robust feature for speech recognition. The second kind consists of mono-lingual emotion recognition experiments by using the Taiyuan University of Technology (TYUT) and the Berlin databases. As the average recognition rate of ZCMT approach is 82.19%, the results indicate that the ZCMT features can characterize speech emotions in an effective way. The third kind consists of cross-lingual experiments with three languages. As the accuracy of ZCMT approach only reduced by 1.45%, the results indicate that the ZCMT features can characterize emotions in a language independent way.展开更多
Valeo, involved in engine cooling fan system design for many years, is interested in noise prediction tools for axial fans. Thus, this paper describes a two-part study of tonal noise computation. The first part deals ...Valeo, involved in engine cooling fan system design for many years, is interested in noise prediction tools for axial fans. Thus, this paper describes a two-part study of tonal noise computation. The first part deals with the prediction of tonal noise using analytical models. As for the second part, it describes a hybrid approach for predicting tonal noise where the sources are extracted from an Unsteady Reynolds-Averaged Naviers-Stocks （URANS） simulation and then propagated into the far, free field using the Ffowcs Williams and Hawkings＇ acoustic analogy. The computational domain is meshed with 46 million polyhedral elements and the simulation takes into account the exact geometry of the rotor blades, the stator blades and the shroud. The results from the first part show that analytical models can be used for comparisons between different fan geometries, but are unable to provide accurate noise predictions compared to experimental results. The simulation shows non-periodic blade loading over a whole fan revolution, and different blade loading between the blades. This introduces some bias in the assessment of the acoustic performance of the fan. Overall, the results from the hybrid method are in accordance with the experimental results.展开更多
文摘Two discriminative methods for solving tone problems in Mandarin speech recognition are presented. First, discriminative training on the HMM （hidden Markov model） based tone models is proposed. Then an integration technique of tone models into a large vocabulary continuous speech recognition system is presented. Discriminative model weight training based on minimum phone error criteria is adopted aiming at optimal integration of the tone models. The extended Baum Welch algorithm is applied to find the model-dependent weights to scale the acoustic scores and tone scores. Experimental results show that tone recognition rates and continuous speech recognition accuracy can be improved by the discriminatively trained tone model. Performance of a large vocabulary continuous Mandarin speech recognition system can be further enhanced by the discriminatively trained weight combinations due to a better interpolation of the given models.
基金Supported by the Innovation Fund Project from Ministry of Science and Technology of China (08C26214401239)
文摘Mercury sphygmomanometer (MSM) is reliable and widely used in clinics and hospitals. The principle of Korotkoff sounds method (KSM) applied in the MSM is also a gold standard to measure blood pressure. Many efforts have been made attempting to replace MSM, which is criticized for being not healthy and safe. In this research, an electronic blood pressure monitor, named K-sounds electronic sphygmomanometer (KESM), was designed as a substitute to MSM. The three key elements of KSM were proposed for the first time. We used appropriate electronic components to build the KESM which can fulfill the functions related to the three key elements. The KESM, which was easy to operate and free of mercury, followed the same principle as MSM. The same principle guaranteed the comparable accuracy. We took equivalence test and the results showed that the designed KESM was as accurate as the calibrated standard MSM. The designed KESM passed the certifications of SFDA and is qualified in clinics or hospitals for diagnostic purposes.
基金Project(61072087)supported by the National Natural Science Foundation of ChinaProject(2010011020-1)supported by the Natural Scientific Foundation of Shanxi Province,ChinaProject(20093010)supported by Graduate Innovation Fundation of Shanxi Province,China
文摘Based on an auditory model, the zero-crossings with maximal Teager energy operator (ZCMT) feature extraction approach was described, and then applied to speech and emotion recognition. Three kinds of experiments were carried out. The first kind consists of isolated word recognition experiments in neutral (non-emotional) speech. The results show that the ZCMT approach effectively improves the recognition accuracy by 3.47% in average compared with the Teager energy operator (TEO). Thus, ZCMT feature can be considered as a noise-robust feature for speech recognition. The second kind consists of mono-lingual emotion recognition experiments by using the Taiyuan University of Technology (TYUT) and the Berlin databases. As the average recognition rate of ZCMT approach is 82.19%, the results indicate that the ZCMT features can characterize speech emotions in an effective way. The third kind consists of cross-lingual experiments with three languages. As the accuracy of ZCMT approach only reduced by 1.45%, the results indicate that the ZCMT features can characterize emotions in a language independent way.
文摘Valeo, involved in engine cooling fan system design for many years, is interested in noise prediction tools for axial fans. Thus, this paper describes a two-part study of tonal noise computation. The first part deals with the prediction of tonal noise using analytical models. As for the second part, it describes a hybrid approach for predicting tonal noise where the sources are extracted from an Unsteady Reynolds-Averaged Naviers-Stocks （URANS） simulation and then propagated into the far, free field using the Ffowcs Williams and Hawkings＇ acoustic analogy. The computational domain is meshed with 46 million polyhedral elements and the simulation takes into account the exact geometry of the rotor blades, the stator blades and the shroud. The results from the first part show that analytical models can be used for comparisons between different fan geometries, but are unable to provide accurate noise predictions compared to experimental results. The simulation shows non-periodic blade loading over a whole fan revolution, and different blade loading between the blades. This introduces some bias in the assessment of the acoustic performance of the fan. Overall, the results from the hybrid method are in accordance with the experimental results.
