Enhanced speech recognition model is now available

2019-05-07 12:34:35
80813
0
Blog picture

Voximplant speech recognition for most of the languages is powered by Google Speech API. At the end of February Google introduced new Speech API capabilities including Enhanced speech recognition model for better quality of recognition (for video and phone calls). According to Google, this model offers the 62-64% Word Error Rate (WER) improvement compared to the standard one. 

WER-comparison

Voximplant developers can use this model by setting model to phone_call_enhanced in ASRParameters:

const asr = VoxEngine.createASR({
	profile: ASRProfileList.Google.en_US,
	model: ASRModelList.Google.phone_call_enhanced,
	singleUtterance: true
})

Please note that billing for enhanced recognition differs from the standard one as it requires more resources.

 

Sign Up for a free Voximplant developer account or talk to our experts

Add your comment

Name*
Email*
Message

Your comment has been added and will be published after moderation.

Recommended posts

How to Send SMS with Node.js

How to Send SMS with Node.js

Voximplant Platform allows developers with any expertise level to send SMS messages in minutes. In this article, we’ll guide you through this development process. You can also watch a video version of this tutorial.