ilyausorov

Really awesome work! I've been trying to do some of this real time back and forth voice coaching myself and it's no easy feat. Congrats on the progress.

For sure the voice standardization model is not perfect, but it was important for us to do especially for the voice privacy. It’s still pretty early tech.

Thanks, we love you too

Yeh they seem to be in the same "major" cluster, although Serbian/Croatian, Romanian, Bulgarian, Turkish, Polish and Czech are all close.

Turkish and Persian seem to be the nearest neighbors.

Plotly is great! Much love.

Yeh, we would've loved to see that too. It's on our roadmap for sure. Same for some of the other languages with a large amount of unique accents like e.g. French, Chinese, Arabic, etc...

Nothing too secret in there! We anonymized everything and anyway it's just a basic Plotly plot. Feel free to check it out.

Good question! It's likely because there are lots of different accents of Spanish that are distinct from each other. Our labels only capture the native language of the speaker right now, so they're all grouped together but it's definitely on our to-do list to go deeper into the sub accents of each language family!

Amazing! If you can make it go viral again too, I will love you!

We did built two free tools, which are geared towards non-native English speakers. You can find them at https://accentoracle.com and https://accentfilter.com. They're less effective for English native speakers, but could still be fun.

Correct, not LLM

Indeed yeah that’s one of the key weaknesses of the approach that we’re using. It overrides the speakers cadence and accent while keeping their voice profile / timbre in place. Different techniques may not do this but also may not copy over the accent to the resulting clip as effectively. So far we’re using this to support pedagogical (and lead-gen) use cases where we think it works sufficiently enough.

Was that right? Or what is the correct native language it should have predicted? Note the %s in the accent breakdown section are prediction probabilities

What if it was already available? Try it out at https://accentfilter.com!

No, the dataset isn't published beyond what you see on the 2D visualization. Sorry.

Thanks, we're doing our best!

We actually did something like this for non-native English speakers a few months back. Check out https://accentoracle.com (most mind-blowing if you're a non native English speaker)

Indeed, although the inference output of the model is based on the ratings input that we trained it on. And that rating input was done by American English native speakers, so this iteration of the model is centered towards those accents more than e.g. UK or Australian or other accents of English from outside the US.

That's a fascinating idea! Definitely something to try out for our team. We actively and continuously do all sorts of experiments with our machine learning models to be able to extract the most useful insights. We will definitely share if we find something useful here.

Sure, that's fair. We apply labels that have a connotation of strength based on the distance, but the underlying calculation is indeed based on distance.

This and more exciting features are coming to the BoldVoice app soon!

For sure, and I don't think we ever use the term default or neutral. The "the American English accent of our expert accent coach Eliza" is just that -- it's one accent.

As a learning platform that provides instruction to our users, we do need to set some kind of direction in our pedagogy, but we 100% recognize that there isn't just 1 American English accent, and there's lots of variance.

Happy to see a happy BoldVoice user. Please don't hesitate to reach out to our team with feedback or thoughts on how we can continue to improve your learning journey. Helping you succeed is our #1 priority!

For sure we did! The training data we used for this was purposely highly varied to account for these various factors so they don't cause too much bias in the model. But there's also an error rate regardless of how good you make it. We keep improving!

Fair point! When Victor tried to speed up to speak as fast as Coach Eliza, while it sounded somewhat less accented, a few parts of the phrase did get less intelligible. 10 minutes of practice is only a start after all.

Interesting to note that we're also developing a separate measure of intelligibility that will give a separate sense of how intelligible versus accented something is.

Congrats on the launch guys!

BoldVoice has been using GrowthBook for about ~6 weeks or so now, and it was super lucky that we found these guys right as we were considering way more expensive options like Optimizely (...6 figures). The tooling is pretty intuitive and Graham and Jeremy have been providing stellar support. There's still a ton to build here and I'm excited to see what these guys add to the platform.

Look super cool, congrats Anisa! As someone who lives in NYC, and went to NYC public schools, I can attest how important something like this would be, especially for the schools that have limited resources.

We're here for you! If you have any feedback, questions or issues, please reach out to us at founders@boldvoice.com! We're constantly working on improving the app and adding more engaging content.

Hey, thanks for sharing your thoughts.

When it comes to striving for a world where accents don't matter, we feel the same way.

In fact, our dialect coach, Ron Carlos, slacked me earlier today: "We truly hope that one day accents won’t matter, but until then we have folks who feel embarrassed about their accent which keeps them from showing up with their full selves. We’re here to help those folks feel more confident with their speech."

What we're trying to help users with is learning the physical skills that make up their account: pronunciation, speech rhythm, intonation, stress -- ultimately, how to speak the way they want, with the ultimate goal of helping the user become more confident and clear in their speech. If the way they want to sound is exactly like someone from Jersey, Boston, L.A. or anywhere else, we're happy to support them!

Thanks for trying it out, glad to hear you liked the tech!

We're continuing to improve and expand both the technical capabilities of the pronunciation assessment, as well as add more varied & exciting content that a user can go through.