I'm starting a new project soon and will be interacting with the engineers who develop these types of tools. My background is primarily in M/LWD and I have done very little work on RSS (aside from attending engineering meetings and maintaining their websites).
I've already gotten started but have just about reached the peak of how much Google can inform me. Thanks in advance - I love being able to lean on this community for quality information / resources.
Was talking to a coworker today, because we’ve been drilling in this gnarly silty-clay shale at 15’/hr for a couple days and we’re sliding all over the place. Coworker’s record for BHAs lost was 3 in 7 wells. Sometimes I think that 2,000 years from now when the alien scientists who’ve populated earth will see all those stands and BHAs and wonder if we sacrificed large straws or something to the Rock Gods.
Paper: https://arxiv.org/abs/2112.02926
Abstract: >Applications of deep learning for audio effects often focus on modeling analog effects or learning to control effects to emulate a trained audio engineer. However, deep learning approaches also have the potential to expand creativity through neural audio effects that enable new sound transformations. While recent work demonstrated that neural networks with random weights produce compelling audio effects, control of these effects is limited and unintuitive. To address this, we introduce a method for the steerable discovery of neural audio effects. This method enables the design of effects using example recordings provided by the user. We demonstrate how this method produces an effect similar to the target effect, along with interesting inaccuracies, while also providing perceptually relevant controls.
Repo with video demo & Colab examples: https://github.com/csteinmetz1/steerable-nafx
Submission statement: This has already been making the rounds on a few other subs, but I thought that this was an interesting conference abstract and project. I'm personally interested in the potential for driving a similar process in reverse, i.e., removing distortion rather than adding it. If anyone else has read any good papers pertaining to audio restoration recently, let me know! (I have a pet project to eventually restore some very low-quality audio of a deceased relative, so I've been loosely keeping tabs on ML audio processing, but it's not my primary area.)
