The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and d...The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.展开更多
Inertial measurement unit (IMU) is a standard motion sensor in modern airborne SAR systems. But how to remove its systematic error is a difficult problem, which impacts the improvement of resolution in azimuth. The te...Inertial measurement unit (IMU) is a standard motion sensor in modern airborne SAR systems. But how to remove its systematic error is a difficult problem, which impacts the improvement of resolution in azimuth. The technique of motion compensation presented in this paper, uses the GPS as a reference system to estimate and correct the systematic error of the IMU on the concept of linear unbiased minimum variance (LUMV). This new and effective method achieves very accurate position measurement (both high and low frequency) of the APC in not only short but also long terms, so that it can satisfy the requirement of high resolution airborne SAR. In the last section of the paper, some experimental simulations from raw data are given.展开更多
文摘The use of hidden conditional random fields （HCRFs） for tone modeling is explored. The tone recognition performance is improved using HCRFs by taking advantage of intra-syllable dynamic, inter-syllable dynamic and duration features. When the tone model is integrated into continuous speech recognition, the discriminative model weight training （DMWT） is proposed. Acoustic and tone scores are scaled by model weights discriminatively trained by the minimum phone error （MPE） criterion. Two schemes of weight training are evaluated and a smoothing technique is used to make training robust to overtraining problem. Experiments show that the accuracies of tone recognition and large vocabulary continuous speech recognition （LVCSR） can be improved by the HCRFs based tone model. Compared with the global weight scheme, continuous speech recognition can be improved by the discriminative trained weight combinations.
文摘Inertial measurement unit (IMU) is a standard motion sensor in modern airborne SAR systems. But how to remove its systematic error is a difficult problem, which impacts the improvement of resolution in azimuth. The technique of motion compensation presented in this paper, uses the GPS as a reference system to estimate and correct the systematic error of the IMU on the concept of linear unbiased minimum variance (LUMV). This new and effective method achieves very accurate position measurement (both high and low frequency) of the APC in not only short but also long terms, so that it can satisfy the requirement of high resolution airborne SAR. In the last section of the paper, some experimental simulations from raw data are given.
