Tech blog
-
2021.09.21Why is AmiVoice so accurate? Why does it have so many different voice recognition engines?
Speech recognition is a difficult technology, and it is difficult to achieve a 100% recognition rate. In this article, we will explain why speech recognition is difficult and how AmiVoice is tackling this challenge.
-
2021.09.06What is the difference between "error improvement rate" and "recognition accuracy (recognition rate)" in voice recognition?
The higher the recognition accuracy (recognition rate) of speech recognition, the more difficult it becomes to increase it by another point. This article explains why this is the case using an indicator called "error improvement rate." It also touches on an indicator called WER, which is often used in papers on speech recognition.
Most viewed articles
-
A quick explanation of how speech recognition works!
-
Comparing the speech recognition rates of OpenAI's Whisper and AmiVoice for "conference" audio
-
How to use the AmiVoice API free coupon
New articles
-
How to use Zenn Coupon & Trial
-
How to use coupons for Zenn Spring 2026
-
"Speech segment ratio" as seen in operational data
Category list
- Introduction to Speech Recognition (15)
- How to improve voice recognition accuracy (12)
- I tried developing it (27)
- How to use AmiVoiceAPI(27)
- Comparison and Verification (6)
- Others(10)
Archive
