小波变换实现语音压缩研究

Research on voice compression through wavelet transformation

在确保信号质量的条件下,为了减少存储空间,文章提出了用小波变换实现语音压缩的方法。根据信号能量高,置零系数的百分比也要高的原则,寻求最适合的压缩方式。实验结果表明:对自己录制的Windows PCM格式的wav文件,在保留的信号能量达到96%以上时,用Haar小波进行5层分解,能有效地完成语音压缩。

Under the condition of ensuring the quality of signal, the paper proposes to realize the voice compression through wavelet transformation to reduce storage space.According to the principle that the percentage of the zero coefficient must be in line with that of the high signal energy, it finds out the most suitable compression method. The results of the experiment show that： when the reserved signal energy is over 96%,we can have the WAV document in the format of Windows PCM recorded by oneself decomposed 5 times with the help of Haar wavelet to successfully achieve the voice compression.