In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learni...In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning （AL） is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence （KLD） and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.展开更多
In this paper, the color elements of painting in the package design and color selection are studied, finding that although the color painting on the function of packaging design and color is different, but the color e...In this paper, the color elements of painting in the package design and color selection are studied, finding that although the color painting on the function of packaging design and color is different, but the color elements of painting can be used in the design of the packing. Through the research and analysis, any basic training is useful and necessary, and any basic training is step by step and also whether to study painting masters can learn to essence. It＇s important that design excellent works in the future.展开更多
基金Acknowledgements This study is supported by the National Natural Science Foundation of China （60705019）, the National High-Tech Research and Development Plan of China （ 2006AA010102 and 2007AA01Z417）, the NOKIA project, and the 111 Project of China under Grant No. 1308004.
文摘In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning （AL） is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullback-Leibler Divergence （KLD） and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.
文摘In this paper, the color elements of painting in the package design and color selection are studied, finding that although the color painting on the function of packaging design and color is different, but the color elements of painting can be used in the design of the packing. Through the research and analysis, any basic training is useful and necessary, and any basic training is step by step and also whether to study painting masters can learn to essence. It＇s important that design excellent works in the future.
