Skip to content
#

callcenter

Here are 38 public repositories matching this topic...

yt605155624
yt605155624 commented Jan 6, 2022

目前的多音字使用 pypinyin 或者 g2pM,精度有限,想做一个基于 BERT (或者 ERNIE) 多音字预测模型,简单来说就是假设某语言有 100 个多音字,每个多音字最多有 3 个发音,那么可以在 BERT 后面接 100 个 3 分类器(简单的 fc 层即可),在预测时,找到对应的分类器进行分类即可。
参考论文:
tencent_polyphone.pdf

数据可以用 https://github.com/kakaobrain/g2pM 提供的数据

进阶:多任务的 BERT
![image](https://user-images.githubusercontent.com/24568452

Orpiv Technologies has 7 years tremendous experience in the call center and outsourcing industry. We offer aligned inbound, outbound and sales calling facilities to our clients with satisfactory results. With Orpiv, you have the rare opportunity to redefine the process of communicating with your customers. Cutting-edge technology does not replace a human voice at the other end of the line. With year-round coverage and a wide range of call center services at your disposal, you’ll never miss a call or business opportunity

  • Updated Dec 24, 2020

Click-to-calling is a very old, simple and straight forward technology that can be implemented in many different ways. Using WebRTC is an iteration if this use case, yet it's often easy to miss the opportunity of empowering your calls and customer engagements with simple web technologies. There are various examples of simple yet powerful examples of click-to-calling with help of Voxbone's click2vox.com

  • Updated Mar 13, 2017
  • HTML

Improve this page

Add a description, image, and links to the callcenter topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the callcenter topic, visit your repo's landing page and select "manage topics."

Learn more