lyra

Unless laws exist to prevent this, you can bet that ALL BigTech are doing this, to varying levels. If they are not doing it in your country, you can bet they are doing it in other countries. The US government incentivised them to do this with the PRISM program ( https://en.wikipedia.org/wiki/PRISM ) and showed them the value of collecting user data even if they do not need it (right now) for their services and products. That services like Alexa, Siri, Cortana, Assistant etc. exist with 24x7 listening devices shows that cost is no longer a hurdle in deploying this at scale. And note that they do not have to upload the audio files (which by the way, they can - I remember Google showcasing an audio codec - https://github.com/google/lyra - that is suitable for very low bandwidth, so neither bandwidth nor storage is a big issue today). Today's

They also don't compare with Lyra (https://github.com/google/lyra)

Since Ballard's codec is "AI" based, can you add google's lyrav2 ( https://github.com/google/lyra ) and Facebook's/meta EnCodec ( https://github.com/facebookresearch/encodec ). Also I don't seem to be able to access your page, so there might be error. Finally, when doing opus comparison it's good now to denote if it is using Lace or NoLace decoder post processing filters that became available in opus 1.5 (note, this feature need to be enabled at compile time, and defying decode a new API call needs to be made to force higher complexity decoder) . See https://opus-codec.org/demo/opus-1.5/

I've thought about doing something similar for google's voice compression lyra https://github.com/google/lyra

O nice, I wonder how 3 kbps speech compares to Google's Lyra. https://github.com/google/lyra/releases 1.5 kbps speech is impressive, I wonder how it compares with Codec2 https://github.com/drowe67/codec2 or how all three compare to each other, useful for speech recordings, the only problem is that there is no widespread support yet.

Very impressive. It'd be interesting to see what the lift would be to get encoding & decoding running in webassembly/wasm. Further, it'd be really neat to try to take something like the tflife_model_wrapper[1] and to get it backed by something like tsjs-tflite[2] perhaps running atop for example tfjs-backend-webgpu[3]. Longer run, the web-nn[4] spec should hopefully simplify/bake-in some of these libraries to the web platform, make running inference much easier. But there's still an interesting challenge & question, that I'm not sure how to tackle; how to take native code, compile it to wasm, but to have some of the implementation provided else-where. At the moment, Lyra V2 can already use XNNPACK[4], which does have a pretty good wasm implementation. But trying to swap out implementations, so for example we might be able to use the GPU o

> It is over 6Kbps Opus[1]. The overhead from packet headers to send data every 40ms is 9.6kbps, is the difference between 12.6Kbps and 17.6Kbps meaningful at that point? We are sending the same number of packets, likely with the same packet loss rate. > A RaspberryPi Zero will provide more than sufficient power for Lyra A Raspberry Pi Zero can't run Lyra, as the proprietary math kernel is only offered in compiled form for x86-64 and android-arm64: https://github.com/google/lyra#license