Silent speech with ultrasound

基于超声波的无声语音

HN Points: 92 / 20 comments | Author: chrwn | HN Discussion: item?id=48825216 | Source: alephneuro.com

Original Article

For comparison, lip-reading achieves 12.5% word error rate on a 1M hour dataset. We're excited that our system approaches existing methods despite being an early investigation trained on a 50-hour dataset and done in just a month.

⋯ 继续阅读请登录会员 ⋯