依据互信息理论提出的互信息匹配识别模型MIM(Mutual Information Matching),能够有效地综合处理语音信号的统计分布特征与时变分布特征,并具有较强的鲁棒性。介绍了运用互信息进行说话人模式匹配的原理,探讨了基于文本的说话人识别中MI...依据互信息理论提出的互信息匹配识别模型MIM(Mutual Information Matching),能够有效地综合处理语音信号的统计分布特征与时变分布特征,并具有较强的鲁棒性。介绍了运用互信息进行说话人模式匹配的原理,探讨了基于文本的说话人识别中MIM模型的应用,通过说话人辨别实验对MIM模型的性能进行了实验分析,并与其它识别模型DTW和GMM进行了比较。对18名男性和12名女性组成的30名说话人进行的识别实验表明, MIM模型的说话人识别性能较好,在采用LPCC特征参数的情况下,平均错误识别率为1.33％。展开更多
An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is jud...An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.展开更多
This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were...This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were built based on simple and complex templates respectively, and the complex one gave better conversion result. Furthermore, conversion trigger pair of y A → y B cBwas proposed to extract the long-distance constrain feature from the corpus; and then Average Mutual Information (AMI) was used to se-lect conversion trigger pair features which were added to the ME model. The experiment shows that conver-sion error of the ME with conversion trigger pairs is reduced by 4% on a small training corpus, comparing with HMM smoothed by absolute smoothing.展开更多
The collective revelation of credit institutions as regards the imminence of specific risks materialising, which often follows long periods of underestimating probable losses, can trigger a broad-based financial delev...The collective revelation of credit institutions as regards the imminence of specific risks materialising, which often follows long periods of underestimating probable losses, can trigger a broad-based financial deleveraging via an overly high upsurge in banks＇ risk premiums vis-a-vis the dynamics of fundamentals underlying loan repayment capability. In this context, this paper seeks to investigate the banking sector＇s internal mechanisms that might bring about a negative spiral of credit risk by building a model for the interaction between the increase of the risk premium and that of net interest income and provisioning rate. Statistical results confirm that a higher risk premium is one of the major determinants of credit default in Romania and its excessive widening could affect financial stability in Romania.展开更多
文摘依据互信息理论提出的互信息匹配识别模型MIM(Mutual Information Matching),能够有效地综合处理语音信号的统计分布特征与时变分布特征,并具有较强的鲁棒性。介绍了运用互信息进行说话人模式匹配的原理,探讨了基于文本的说话人识别中MIM模型的应用,通过说话人辨别实验对MIM模型的性能进行了实验分析,并与其它识别模型DTW和GMM进行了比较。对18名男性和12名女性组成的30名说话人进行的识别实验表明, MIM模型的说话人识别性能较好,在采用LPCC特征参数的情况下,平均错误识别率为1.33％。
基金The National Natural Science Foundation of China(No.60972001)the Science and Technology Plan of Suzhou City(No.SS201223)
文摘An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.
基金Supported by the National Natural Science Foundation of China as key program (No.60435020) and The HighTechnology Research and Development Programme of China (2002AA117010-09).
文摘This paper applied Maximum Entropy (ME) model to Pinyin-To-Character (PTC) conversion in-stead of Hidden Markov Model (HMM) that could not include complicated and long-distance lexical informa-tion. Two ME models were built based on simple and complex templates respectively, and the complex one gave better conversion result. Furthermore, conversion trigger pair of y A → y B cBwas proposed to extract the long-distance constrain feature from the corpus; and then Average Mutual Information (AMI) was used to se-lect conversion trigger pair features which were added to the ME model. The experiment shows that conver-sion error of the ME with conversion trigger pairs is reduced by 4% on a small training corpus, comparing with HMM smoothed by absolute smoothing.
文摘The collective revelation of credit institutions as regards the imminence of specific risks materialising, which often follows long periods of underestimating probable losses, can trigger a broad-based financial deleveraging via an overly high upsurge in banks＇ risk premiums vis-a-vis the dynamics of fundamentals underlying loan repayment capability. In this context, this paper seeks to investigate the banking sector＇s internal mechanisms that might bring about a negative spiral of credit risk by building a model for the interaction between the increase of the risk premium and that of net interest income and provisioning rate. Statistical results confirm that a higher risk premium is one of the major determinants of credit default in Romania and its excessive widening could affect financial stability in Romania.
