Mobile, Hands-free, Silent Speech Texting Using SilentSpeller
Autor: | Alex Olwal, Tan Gemicioglu, Richard Li, Naoki Kimura, Jonathan Womack, Thad Starner, Yuhui Zhao, Abdelkareem Bedri, Jun Rekimoto |
---|---|
Rok vydání: | 2021 |
Předmět: |
Computer science
Character (computing) Speech recognition 05 social sciences Wearable computer 020207 software engineering 02 engineering and technology Speaker recognition Spelling Silent speech interface 0202 electrical engineering electronic engineering information engineering Voice 0501 psychology and cognitive sciences Words per minute 050107 human factors Word (computer architecture) |
Zdroj: | CHI Extended Abstracts |
Popis: | Voice control provides hands-free access to computing, but there are many situations where audible speech is not appropriate. Most unvoiced speech text entry systems can not be used while on-the-go due to movement artifacts. SilentSpeller enables mobile silent texting using a dental retainer with capacitive touch sensors to track tongue movement. Users type by spelling words without voicing. In offline isolated word testing on a 1164-word dictionary, SilentSpeller achieves an average 97% character accuracy. 97% offline accuracy is also achieved on phrases recorded while walking or seated. Live text entry achieves up to 53 words per minute and 90% accuracy, which is competitive with expert text entry on mini-QWERTY keyboards without encumbering the hands. |
Databáze: | OpenAIRE |
Externí odkaz: |