A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality And Latency

This video program is a part of the Premium package:

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality And Latency


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality And Latency

0 views
  • Share
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In t
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In t