1.8～2.4kbps多带激励语音编码器

Multiband excitation coding of speech at 1.8~2.4 kbps

在多带激励（MultiBand Excitation,MBE）语音模型的基础上提出了一种基于基音处频域误差函数特性的快速基音细搜索算法和一种基于 MBE-LPC与 VDVQ（Variable-Dimension Vector Quantization）的可分级谱幅度矢量量化方案,实现了一种 1.8～2.4 kbps可分级的 MBE语音编码器。实验结果表明木文所实现 MBE编码器在保持与常规同速率的MBE-VDVQ合成质量相当的同时能大幅度减少所需的运算量和存储空间。

A new fast pitch-refining algorithm of MBE model, which is based on the feature of frequency domain error function around pitch, and a new scalable quantization scheme of spectral envelope magnitude, which is based on MBE-LPC model and Variable-Dimension Vector Quantization (VDVQ), are proposed. A 1.8 - 2.4 kbps scalable MBE coder is implemented with the new pitch-refining algorithm and the new quantization scheme. Experiment result shows that this MBE coder achieves the same synthesis quality as the original MBE-VDVQ coder in the same bit rate with much less computation and memory .