eternal_virgin
Joined 7 years ago
Joined 7 years ago
For example in predictive typing anything above ~100ms (don't remember the number but there's an exact measurement on the Gmail paper for smart compose) is noticeable and very annoying to a user.
Or video chat, I'd be curious to see the video latency required for a user to notice lag between audio & video.
I know in game dev, I was always taught that 60fps is fine, but then there are gamers swearing up and down when they drop below 140fps. Would be curious to see what the max allowed latency is here as well.
Another common one is the microexpressions latency which is frequently quoted as 1/20 of a second (max latency before an emotion detector starts to miss the microexpression).
I feel like these are the real goalposts in tech; especially in ML, we've got the accuracy/quality and now we need the speed. Every research paper likes to brag about how many ms it takes for one step, I'd like to see this compared to the maximum latency required for practical HCI.
We store no speech data at all! On Google Chrome, speech recog is done via Web Speech API. They claim not to store speech data in their privacy whitepaper: https://www.google.com/chrome/privacy/whitepaper.html#speech
- works right in your browser with no downloads or installs - comes with all the cool video call features (screenshare, chat, picture in picture) - integrates speech recognition to provide subtitles and a full call transcript!
We're also trending #1 on Product Hunt right now! There's a 7 day trial so you can try it out, and we'd love to get feedback: https://www.producthunt.com/posts/aiko-meet
Also do AWS credits apply to this? I and most startup founders I know have upwards of 30k$ in AWS credits usually sitting around so this would definitely go a long way as to integrating translation without running a pre-scale cost.
According to their support the only way to change basically anything is to open an entirely new account. So we're currently tracking down and collecting documents all over again, except this time we have to spend a bunch on legal fees since we had Atlas to help us through the first time.
And thank god, HTTPS support built in... it never ceases to amaze me why some HTTP libs don't have TLS as a given.