基于DIVA模型的语音-映射单元自动获取

Automatic acquisition of speech sound-target cells based on DIVA model

针对DIVA模型中存在的"感知能力与语音生成技巧发育不平衡"问题,提出了一种自动获取语音-映射单元的方法.该方法将人耳模拟为一个具有不同带宽的并联带通滤波器组,分别与模型中21维度的听觉存储空间相关联,对不同听觉的不同反应,分别考虑其频带的屏蔽效应、听觉响度与频率的关系.在读取语音输入信号的过程中,模型能较好地获得初始听觉表示,其方式与婴儿咿呀学语的过程基本一致.仿真实验表明,通过边界定义、相似性比较以及搜索更新等步骤,此方法能很好地进行初始输入模式的自组织匹配,并最终使DIVA模型更具语音获取的自然特性.

Contraposing the shortage of Directions Into Velocities of Articulators（ DIVA） model about＂infants perceptual abilities do develop faster at first than their speech production skills＂,the paper presents an automatic acquisition method of speech sound-target cells. The method simulates the human ear as a parallel band-pass filter group with different bandwidth and associates respectively; the filter with the 21-dimensional storage space of auditory sense in DIVA model. This method was done in order for different auditory reactions,the shielding effect of frequency band,sound loudness,and frequency relation could be considered respectively for this study. In the process of reading the input signal of speech,the model can acquire good initial hearing and the process is consistent with baby ＇s babble. The simulation results show that through boundary definition,similarity comparison,searching and updates and so on,the method has nicer self-organized pattern matching effect for initial input,which makes the DIVA model a more natural characteristic regarding speech acquisition.