白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Haptic communication system using cutaneous actuators for simulation of continuous human touch

專利號(hào)
US10867526B2
公開(kāi)日期
2020-12-15
申請(qǐng)人
Facebook, Inc.（US CA Menlo Park）
發(fā)明人
Ali Israr; Freddy Abnousi; Frances Wing Yee Lau
IPC分類
H04B3/36; G09B21/00; G01L5/00; G06N20/00; G06N3/04; G06N3/08; G10L13/00; G10L21/02; G08B6/00; G09B21/04; G10L15/02; G10L15/22; G10L21/0272; G06F3/01; G06F3/16; G10L25/18; G10L25/48; G10L19/00; G10L15/16; G10L21/06
技術(shù)領(lǐng)域
haptic,cutaneous,actuator,actuators,signals,speech,in,phoneme,may,vibrations
地域： CA CA Menlo Park

摘要

A haptic communication device includes an array of cutaneous actuators to generate haptic sensations corresponding to actuator signals received by the array. The haptic sensations include at least a first haptic sensation and a second haptic sensation. The array includes at least a first cutaneous actuator to begin generating the first haptic sensation at a first location on a body of a user at a first time. A second cutaneous actuator begins generating the second haptic sensation at a second location on the body of the user at a second time later than the first time.

說(shuō)明書(shū)

The machine learning engine 1760 includes a feature extractor 1762 and a machine learning model 1766. The feature extractor 1762 extracts a feature vector 1764 from the speech signals 1706 and transmits the feature vector 1764 to the machine learning model 1766 as shown in FIG. 17D. The feature extractor 1762 may be implemented in software, hardware, or a combination thereof. The feature vector 1764 may represent amplitudes of frequency bands of the speech signals 1706. These frequency bands may be obtained by decomposing the speech signals 1706 into the frequency bands by the feature extractor 1762, the machine learning engine 1760, or another component of the envelope encoder 1716. For example, an array of band-pass filters that span the speech spectrum may be used to decompose the speech signals 1706 into the frequency bands. The operation of the feature extractor 1762 and the feature vector 1764 are illustrated and described in detail above with reference to FIGS. 4 and 13A-13D.

The machine learning engine 1760 may use supervised machine learning to train the machine learning model 1766 with feature vectors from a positive training set and a negative training set serving as the inputs. Different machine learning techniques—such as linear support vector machine (linear SVM), boosting for other algorithms (e.g., AdaBoost), neural networks, logistic regression, na?ve Bayes, memory-based learning, random forests, bagged trees, decision trees, boosted trees, or boosted stumps—may be used in different embodiments.

權(quán)利要求

1
微信群二維碼
意見(jiàn)反饋