将ETSI ES 202 050 V.1.1.3版本规定的Mel域上的两级维纳滤波结构推广到分数Mel域上,基于3周期的离散分数余弦变换,提出了分数Mel域上的两级维纳滤波结构,获得了性能的提高;针对以上两种方法的计算量较大和引入了时域截断噪声等缺点,提...将ETSI ES 202 050 V.1.1.3版本规定的Mel域上的两级维纳滤波结构推广到分数Mel域上,基于3周期的离散分数余弦变换,提出了分数Mel域上的两级维纳滤波结构,获得了性能的提高;针对以上两种方法的计算量较大和引入了时域截断噪声等缺点,提出了分数余弦变换域上的两级最佳线性滤波。理论分析和实验结果表明,该算法具有明显的降噪作用,能够应用于语音识别系统前端处理中。展开更多
This paper presents a quantization skipping method for H. 264/AVC video coding standard. In order to reduce the conputational-cost of quantization process coming from integer discrete cosine transform of H. 264/AVC, a...This paper presents a quantization skipping method for H. 264/AVC video coding standard. In order to reduce the conputational-cost of quantization process coming from integer discrete cosine transform of H. 264/AVC, a quantization skipping condition is derived by the analysis of integer transform and quantization procedures. The expeerimental results show that the proposed algorithm has the capability to reduce the computional cost about 10% -2.5%.展开更多
文摘将ETSI ES 202 050 V.1.1.3版本规定的Mel域上的两级维纳滤波结构推广到分数Mel域上,基于3周期的离散分数余弦变换,提出了分数Mel域上的两级维纳滤波结构,获得了性能的提高;针对以上两种方法的计算量较大和引入了时域截断噪声等缺点,提出了分数余弦变换域上的两级最佳线性滤波。理论分析和实验结果表明,该算法具有明显的降噪作用,能够应用于语音识别系统前端处理中。
基金supported by the Seoul Future Contents Convergence(SFCC)Cluster established by Seoul R&BD Program
文摘This paper presents a quantization skipping method for H. 264/AVC video coding standard. In order to reduce the conputational-cost of quantization process coming from integer discrete cosine transform of H. 264/AVC, a quantization skipping condition is derived by the analysis of integer transform and quantization procedures. The expeerimental results show that the proposed algorithm has the capability to reduce the computional cost about 10% -2.5%.