Classification of intended phoneme production from chronic intracortical microelectrode recordings in speech-motor cortex
Classification of intended phoneme production from chronic intracortical microelectrode recordings in speech-motor cortex
复制标题
DOI：
10.3389/fnins.2011.00065
复制
发表时间：
2011-01-01
影响因子：
4.3
通讯作者：
Kennedy, Philip R.
中科院分区：
文献类型：
--
作者：
Brumberg, Jonathan S.;Wright, E. Joe;Kennedy, Philip R.
我们进行了一项神经生理学研究，试图在瘫痪的人类志愿者使用慢性微电极记录的语音生产。这名志愿者患有闭锁综合征，使他处于几乎完全瘫痪的状态，尽管他保持着良好的认知和感觉。在这项研究中，我们调查了可行性的监督分类技术预测的预期音素生产的情况下，任何明显的运动，包括讲话。这种分类或解码能力有可能通过提供与一般社区的直接沟通联系，大大改善许多无法说话的人的生活质量。我们研究了三个分类器的多类歧视问题，其中的项目是38个美国英语音素，包括单元音和双元音元音和辅音的性能。这三个分类器的性能不同，但平均整体准确率在16%至21%之间（机会水平为1/38或2.6%）。此外，统计分类以上的机会音素的分布是不均匀的，虽然20的38个音素进行了分类，所有三个分类器的统计意义。这些初步结果表明，监督分类技术能够进行大规模的多类歧视，试图语音生产，并可能为未来的通信假肢的基础。
We conducted a neurophysiological study of attempted speech production in a paralyzed human volunteer using chronic microelectrode recordings. The volunteer suffers from locked-in syndrome leaving him in a state of near-total paralysis, though he maintains good cognition and sensation. In this study, we investigated the feasibility of supervised classification techniques for prediction of intended phoneme production in the absence of any overt movements including speech. Such classification or decoding ability has the potential to greatly improve the quality-of-life of many people who are otherwise unable to speak by providing a direct communicative link to the general community. We examined the performance of three classifiers on a multi-class discrimination problem in which the items were 38 American English phonemes including monophthong and diphthong vowels and consonants. The three classifiers differed in performance, but averaged between 16 and 21% overall accuracy (chance-level is 1/38 or 2.6%). Further, the distribution of phonemes classified statistically above chance was non-uniform though 20 of 38 phonemes were classified with statistical significance for all three classifiers. These preliminary results suggest supervised classification techniques are capable of performing large scale multi-class discrimination for attempted speech production and may provide the basis for future communication prostheses.