Adaptive Resonance Situated for Articulatory Speech Learning and Synthesis
Adaptive Resonance Situated for Articulatory Speech Learning and Synthesis
复制标题
用于发音学习和合成的自适应共振
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
M. Brady
中科院分区：
文献类型：
--
作者：
M. Brady
介绍了机器人声道的控制框架。我将时序编排机制融入到基本的 ART 网络中，并且该网络位于语音感知-产生环路中。该网络首先经过训练，在“牙牙学语学习”阶段将其电机输出与其产生的声音输入自动关联。进一步的训练包括交替学习牙牙学语和学习一组预先合成的节奏元音模式。初步分析表明，该网络成功地区分和再现了具有正确时间结构的训练模式。索引术语 – 自适应共振理论、ART、语音处理、机器人动力学、小脑模型算法
A control framework for a robotic vocal tract is introduced. I incorporate a timing orchestration mechanism into a basic ART network and the network is situated within a speech perception-production loop. The network is first trained to autoassociate its motor output with its resulting sound input during a ‘babble learning’ phase. Further training involves alternating between babble learning and learning for a set of pre-synthesized rhythmic vowel patterns. Preliminary analysis indicates that the network is successful at distinguishing and reproducing the training patterns with their correct temporal structures. Index Terms – adaptive resonance theory, ART, speech processing, robot dynamics, cerebellar model arithmetic