New voice AI tools
-
With the advent of voice AI tools that can mimic any voice based on a sample input, curious if the devs have considered using this tech to cleanup the ATC comms? We all love the original voices from 4.0, but the pieces that have been added after the fact are a bit lacking. For instance, the added “cleared for overhead” response sounds nothing like the male or female ATC voice. I know what has been done was needed, and I’m not knocking it at all, just wondering if we could look at this for an upcoming release? And of course thank you all for the hard work and dedication you put in to this amazing sim!
-
@luvtofish said in New voice AI tools:
With the advent of voice AI tools that can mimic any voice based on a sample input, curious if the devs have considered using this tech to cleanup the ATC comms? We all love the original voices from 4.0, but the pieces that have been added after the fact are a bit lacking. For instance, the added “cleared for overhead” response sounds nothing like the male or female ATC voice. I know what has been done was needed, and I’m knocking it at all, just wondering if we could look at this for an upcoming release? And of course thank you all for the hard work and dedication you put in to this amazing sim!
we already use AI generated voice, contact @Micro_440th
-
@Mav-jp I wasn’t aware it is being used, maybe the example I sited was missed or was not properly reconstructed? The new Microsoft product seems pretty incredible and only needs a 3 sec sample.
-
@luvtofish said in New voice AI tools:
@Mav-jp I wasn’t aware it is being used, maybe the example I sited was missed or was not properly reconstructed? The new Microsoft product seems pretty incredible and only needs a 3 sec sample.
only a very limited number of frags have been done with AI tools
Feel free to contact @Micro_440th if you want to add you stone in bMS by redoing all frags that have been badly done in the past
-
@luvtofish
Cloned falcon voicesI use this methodology for ATC voices for many of the theaters not developed directly by the BMS devs.
Regards, -
hopefully we’ll never replace Lt Cmdr Stephen Hawking as LSO
-
@airtex2019 said in New voice AI tools:
hopefully we’ll never replace Lt Cmdr Stephen Hawking as LSO
I read that in his voice.
-
I’m not a BMS developer, but have recently been in touch with @Tomcattwo, @Boxer, @Micro_440th and @Mav-jp about implementing voice synthesis. Additionally, to further improve the AI voices, it might be an option to have them go through the same sound processing that’s done to voice chat at the moment. But that is lower priority.
After discussing it with @Boxer, we split the project into phases:
- Generate convincing new frags using text-to-speech (TTS). This way we could expand the possibilities of AI communication without any new recordings or code changes.
- If step 1 results in a usable voice model, I could use it to evaluate the computation needed for realtime TTS. Hopefully, this will give us enough information to determine how TTS might affect the sim and rendering processing. If performance is affected too much, realtime TTS might not be a good fit for BMS.
- Somewhere parallel to all this, we might still consider trying to route the AI voices through the signal processing in IVC.
I’m lucky enough to have access to a GPU cluster at my work. Unfortunately, the GPUs aren’t always available because researchers tend to use them for actual science. But in between their work I’ve been training a multispeaker voice model based on the existing BMS frags. I think the result can still be improved, but I’ll try to share some progress soon. The good news is that if it works, it will immediately work for every existing voice in BMS.