2021
DOI: 10.1145/3463519
|View full text |Cite
|
Sign up to set email alerts
|

SonicASL

Abstract: We propose SonicASL, a real-time gesture recognition system that can recognize sign language gestures on the fly, leveraging front-facing microphones and speakers added to commodity earphones worn by someone facing the person making the gestures. In a user study (N=8), we evaluate the recognition performance of various sign language gestures at both the word and sentence levels. Given 42 frequently used individual words and 30 meaningful sentences, SonicASL can achieve an accuracy of 93.8% and 90.6% for word-l… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 33 publications
(4 citation statements)
references
References 66 publications
0
4
0
Order By: Relevance
“…). The reliability of the system increases as more pictures of each character are saved used in equation (12). Segmentation methods based on pixels and regions can be used.…”
Section: Automatic Behavioral Analysis Employing Gesture Detection Fr...mentioning
confidence: 99%
“…). The reliability of the system increases as more pictures of each character are saved used in equation (12). Segmentation methods based on pixels and regions can be used.…”
Section: Automatic Behavioral Analysis Employing Gesture Detection Fr...mentioning
confidence: 99%
“…The accuracy was 94.2%. In addition, SonicASL [ 26 ] leveraged dual speakers and microphones to capture the sonic feedback from hand gestures. Given 42 frequently used ASL words and 30 sentences, the system could achieve an accuracy of 93.8% at the word level, and 90.6% at the sentence level.…”
Section: Introductionmentioning
confidence: 99%
“…The summary of previous studies is listed in Table 1. EMG & IMU sensors 150 -8 [20] EMG & ACC sensors 121 -1 [24] Customized data glove 26 -3 [25] Smartwatch & Smart ring 100 -10 [26] Speaker & Microphone 42 30 8 In the above-mentioned studies on sign language recognition using wearable sensors, more studies focused on single gestures. Few datasets for sentence recognition were confined to a limited number of sentences and did not consider grammatical inconsistencies between sign language and spoken language.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation