RU version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
57% Positive
Analyzed from 263 words in the discussion.
Trending Topics
#voice#accent#own#app#https#reference#british#american#training#someone

Discussion (7 Comments)Read Original on HackerNews
So now I’m curious if our two applications use the same approach under the hood! I have a detailed tech stack rundown on this page: https://own-voice-dev.netlify.app/#/info but in brief I use OpenVoice v2 to convert someone’s voice toward a differently-gendered reference voice, but leave it at only like 30%-60% transformed so it still sounds like them and not the reference. This transformed voice then becomes a practice reference for drilling.
I know it’s bad form to discuss that, but this is a completely normative comment, with no opinion given so far from being a flame. And it adds to the technical discussion!
I tried a few, I think the British American was maybe the best one. I didn't really notice a huge difference on Italian or Indian accent.
British - American https://pastewaves.com/player/25cacf64-461a-4eef-9b02-9bc0da...
A little shaky, but no doubt hints of a British Accent.
Why? You run across many people with accents every day, right? Well, it’s a problem; people definitely treat you differently.
This issue isn’t specific to the USA btw, it’s just I’ve been working in the USA for a long time.