搜索结果: 1-2 共查到“理论语言学 WFST Models”相关记录2条 . 查询时间(0.062 秒)
A 6mW, 5,000-Word Real-Time Speech Recognizer Using WFST Models
industry-standard WFST GMM speech models
2015/3/9
Abstract—We describe an IC that provides a local speech recognition capability for a variety of electronic devices. We start with a
generic speech decoder architecture that is programmable with indus...
Hardware-accelerated speech recognition is needed to supplement today’s
cloud-based systems in power- and bandwidth-constrained scenarios such as
wearable electronics. With efficient hardware speech...