Abstract
Abstract
Objective. Silent speech recognition based on surface electromyography has been studied for years. Though some progress in feature selection and classification has been achieved, one major problem remains: how to provide confident or reliable prediction. Approach. Inductive conformal prediction (ICP) is a suitable and effective method to tackle this problem. This paper applies ICP with the underlying algorithm of random forest to provide confidence and reliability. We also propose a method, test time data augmentation, to use ICP as a way to utilize unlabelled data in order to improve prediction performance. Main Results. Using ICP, p-values and confidence regions for individual predictions are obtained with a guaranteed error rate. Test time data augmentation also outputs relatively better conformal predictions as more unlabelled training data accumulated. Additionally, the validity and efficiency of ICP under different significance levels are demonstrated and evaluated on the silent speech recognition dataset obtained by our own device. Significance. These results show the viability and effectiveness of ICP in silent speech recognition. Moreover, ICP has potential to be a powerful method for confidence predictions to ensure reliability, both in data augmentation and online prediction.
Funder
National Natural Science Foundation of China
Autonomous Research Project of the State Key Laboratory of Industrial Control Technology, China
Subject
Cellular and Molecular Neuroscience,Biomedical Engineering
Reference46 articles.
1. 2nd ed The complete human body: the definitive visual guide (Great Britain: Dorling Kindersley);Alice,2016
2. Speech synthesis from neural decoding of spoken sentences;Anumanchipalli;Nature,2019
3. Random forests;Breiman;Mach. Learn,2001
4. Myo-electric signals to augment speech recognition;Chan;Med. Biol. Eng. Comp.,2001
5. Visible and near infrared spectroscopy coupled to random forest to quantify some soil quality parameters;de Santana;Spectrochim. Acta,2018
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献