Posts on Evan King

Engram: Generative audio sampler

Tue, 10 Feb 2026 00:00:00 +0000

TL;DR: I’m launching the Engram, a hardware sampler that generates new sounds in real-time using embedded generative audio models. It combines traditional sampling with voice control and audio “model bending”, giving musicians new ways to explore and create unique sounds.

Contact me or sign up as a tester to help shape Engram’s future. EDIT: The call for testers is now closed.

How do we make AI art less boring?

People have mixed feelings about AI. Everyone I talk to – from engineers to physicians to artists – agrees on one thing: AI changes their relationship with their labor. The response to this, however, varies quite a bit. This ambivalence is most apparent in creative fields, where AI boosters are selling the ability to generate whole books, movies, albums, and works of visual art from a few prompts. From an efficiency perspective, this is optimal. But art has never been about efficiency: it’s about history, the artist’s abilities and limits, and the artistic process. Many artists are responding to these efficiency promises with rightful animus and distrust. The artists, in fact, are not the customer. Their bosses are.

Mishearings: Turning ASR models into poets

Tue, 11 Feb 2025 00:00:00 +0000

TL;DR: I built a tool for assembling Dadaist poems from ASR transcriptions of misheard speech, and you can play with it in your web browser. I built it with my MoonshineJS library, Tone.js, and p5js.

Introduction

My goal lately has been to build a JS library for simple on-device speech recognition in web applications. While there are many practical uses for this, I felt the urge recently to explore its creative potential. Speech recognition models are a bit more utilitarian than purely generative models – you put speech in and get text out – so I had my work cut out for me.

A private ambient summarizer device

Fri, 03 Jan 2025 00:00:00 +0000

An ePaper display shows the most common words overheard from nearby conversations.

I wrapped up my PhD recently. It’s in “Electrical and Computer Engineering”, though it’s more descriptive to say that I spent my four years of graduate school working in “Ubiquitous Computing” or ubicomp. Ubicomp researchers aim to make technology that “fit[s] the human environment” rather than forcing humans to adapt themselves to environments dominated by obtrusive technology. Established by the late Mark Weiser at Xerox PARC in the early nineties, ubicomp has philosophical roots: Weiser was strongly influenced by the idea of “entanglement”, which suggests that humans are inextricably linked to (and influenced by) their surroundings.

Moonshine: Industry-leading edge ASR

Mon, 21 Oct 2024 00:00:00 +0000

Moonshine outperforms speech-to-text models from OpenAI, Google, NVIDIA, and Meta on the OpenASR Leaderboard while running 5x faster¹ on edge devices.

I built the data collection and preprocessing pipelines that we used to train Moonshine, delivering over 200K hours of labeled data. We needed a LOT of good data, and we had to move fast. The pipeline I constructed was massively distributed, allowing us to intake hundreds of terabytes of raw audio data, label it, and clean it within the span of several weeks.

Teaching things to think

Mon, 06 May 2024 00:00:00 +0000

What if smart devices could reason about their state, like a thermostat that explains its schedule, or a light bulb that chooses a color to suit a mood?

That’s the subject of my IEEE PerCom ‘25 paper, “Teaching Things To Think: Bootstrapping Local Reasoning for Smart(er) Devices”. We proposed a method for synthesizing training data to distill small language models for the task, leveraging a combination of formal methods and generative models. We ultimately trained and evaluated models for two “thoughtful things” – a lamp and a thermostat – then evaluated their performance at explaining and mutating their state in response to unconstrained user commands.

Sasha: Introducing LLMs for smart spaces

Wed, 06 Mar 2024 00:00:00 +0000

Building on my weekend project to control some smart lights with ChatGPT, this wide-ranging paper fully introduces LLM-based reasoning to multi-device smart home environments. We introduce methods and benchmarks for measuring model performance at reasoning in smart homes, propose methods for engineering immediate and scheduled responses to user goals, propose a multi-step reasoning system for improving system performance, and conduct the first user study of a real LLM-controlled smart home.

Something that often gets lost in a research paper is the truly fun and challenging experiences you can have with the work. Between touring a trailer on the UT Austin JJ Pickle Campus to see if I could turn it into a smart home (I could not – it was outfitted with extremely sensitive equipment for conducting ventilation studies) to eventually hauling pegboard and furniture from my illegally-parked RAV4 up to an unused lab on the 7th floor of the EER building, this project was truly the highlight of my PhD.

Adding eurorack features to a tape recorder

Sat, 30 Dec 2023 00:00:00 +0000

One of my favorite pieces of music hardware is a 4-track TASCAM Porta 03 mkII tape recorder that I acquired back in ~2013. Having grown up with a DAW, I’d gotten the itch to record music with some self-imposed creative limitations, and a coworker at the time kindly gifted it to me (thanks Carol, if you’re out there). Though I’ve yet to use it for producing any full songs, it has found a home in my modular synth setup. I use it there to record, manipuate, and play back tape loops.

The Sky Doesn't End at the Top of the Page

Fri, 01 Dec 2023 00:00:00 +0000

Featured on KUTX Song of the Day, November 2023

“The Sky Doesn’t End at the Top of the Page” is a euphoric, genre-hopping exploration of the way our mental models of the world develop—or cease to develop—as we age.

The album’s title recalls a childhood epiphany–the kind that so firmly demarcates iterations of our understanding of the world that we retain a memory of it long into adulthood. As a child learns to draw, their depiction of the sky begins with scribbles. Yet, as we age, we realize how crude a representation that is: our skies accordingly grow in fidelity, first to include solid blocks of color, then gradients of multiple shades. Our mental models of wants and needs, fact and fiction, and meaning undergo the same incremental progression and occasional plateau. Ultimately, no matter how good the model is, it’s just an estimation. Only through experience, occasional exploration, and repeated failure can we develop an understanding of ourselves, our relationships, and the world around us.

CANDor: Energy efficient neighbor discovery

Mon, 25 Sep 2023 00:00:00 +0000

Bluetooth Low Energy (BLE) can be useful for forming ad-hoc networks between smart devices, and for exchanging information in sensor networks. It’s difficult, however, to choose the right settings for the BLE protocols that devices use to discover one another. The optimal protocol effectively balances discovery latency and packet reception rates with the energy consumed by sending and scanning for neighboring packets.

In this work, I introduce a novel neighbor discovery protocol to improve the packet reception rate and energy consumption of BLE neighbor discovery. Unlike prior work, which uses extra sensors (e.g., GPS) to recalibrate the protocol performance, this work uses the performance of neighbor discovery itself as a signal to determine when to recalibrate the protocol’s settings.

Northern California, Summer 2023

Mon, 01 May 2023 00:00:00 +0000

Shot on Fujifilm Superia 400 with a Canon T50 camera in Sonora, CA and Half Moon Bay, CA.

Using LLMs to control a smart home

Sat, 18 Mar 2023 00:00:00 +0000

2024 UPDATE

I originally authored this post in early 2023 — little did I know it would be the spark of a broader research project, ultimately becoming a significant part of my PhD dissertation. If you are the researchy type, you can read the short 2023 preprint paper and/or the in-depth 2024 ACM IMWUT paper I published and presented at UbiComp 2024 about this topic. We also made a demo video that shows an LLM-based smart home in action. Otherwise, enjoy the original post!

Self-updating pothos timelapse camera

Sun, 25 Sep 2022 00:00:00 +0000

A daily-updated timelapse of my pothos plant.

While I’ve cared for (and killed) a variety of different houseplants over the years, pothos plants are probably my favorite. They are incredibly hardy, easy to propogate from clippings, and they grow quickly. I’ve always been curious to learn a bit more about how these plants maneuver as they grow, so I decided to set up an automated system to monitor mine.

Combining an ESP8266 equipped with a camera, some Philips Hue smart lights, and a Raspberry Pi, this system takes a picture of the plant every hour and prepares a rolling timelapse of the past week every day at midnight. A bit of code handles exposure by balancing out the smart lights in my living room and turning on an overhead light before taking the picture. Another bit of code does some color balancing, yielding a better looking photo. ~~Each day it uploads the latest timelapse to pothos.evanking.io. The timelapse above is the latest, updated automatically.~~ UPDATE: I took this down when I moved in 2023 and haven’t had a chance to put it up again. It was a fun project though, so I’m keeping it here for archival purposes.

My Plants Are Hanging on by a Thread

Fri, 03 Jun 2022 00:00:00 +0000

“My Plants Are Hanging on by a Thread” is a cozy, hazy art-pop exploration of the interplay between everyday human life and the natural world. I released this EP as Olivia Nowadays in 2022 along with my friend and collaborator, Kent Carson.

Blending field recordings with lush instrumentation, warm rhythms, and lyrics imbued with the whimsy of magical realism, the five songs on MPAHOBAT dip in and out of the experiences of different people, animals, and automatons to explore this fraught relationship between human lifestyles and nature.

Curvature of the Earth

Tue, 14 Dec 2021 00:00:00 +0000

Featured in Bandcamp’s New and Notable, December 2021

A series of experimentations by my collaborator Kent Carson and I with a trove of recordings we’d gathered during travels abroad ultimately became the genesis of our musical project and pseudonym Alex Green: an outlet for sonic collages of synth textures, found sounds, and fluid input from collaborators that form a proxy for the lived experience of different locales.

In late 2021, we released “Curvature of the Earth” as Alex Green. Seen through the eyes of Alex as a lone, anonymous traveler, the album is an ambient, spiritual, and sometimes humorous journey drawing upon samples collected around the globe.

Texas Hill Country, 2021

Thu, 11 Nov 2021 00:00:00 +0000

Shot on Fujifilm Superia 400 with a Canon T50 camera in Canyon Lake, TX.

Shot on Kodak Portra 800 with a Canon T50 camera in Austin, TX during the winter storm that caused the 2021 Texas power crisis.

Petri: Cellular rhythm generator for eurorack

Sun, 17 Mar 2019 00:00:00 +0000

Eurorack is an open format for modular synthesizers—hardware-based audio devices that enable you to craft compositions (called “patches”) by routing voltage signals between different modules. Some modules produce sound, others only produce voltages that you can use to build rhythms, melodies, etc. It’s a highly-flexible way of creating music: one that rewards experimentation, and an analytical approach to composition.

Having played with (and made small code contributions to) the open-source modular synthesizer project VCV Rack, I decided sometime in 2019 that I should learn more about the “real thing”. I first started by building popular DIY modules like the Turing Machine and the Penrose and eventually graduated to designing my own module, which I call the petri. I’ve always found computational processes that model natural systems interesting, so I set out to build something with that in mind. Petri (named for Julius Richard Petri, inventor of the Petri dish) embodies that principle, using selectable cellular automata rule sets and starting populations to generate rhythmic sequences of control voltage pulses. It’s like a little ecosystem of cell life in modular form.

From sea levels to music with CSV to MIDI

Wed, 14 Feb 2018 00:00:00 +0000

Data sonification describes the process by which data is translated into sound. There’s a variety of reasons this might be worthwhile, from purely artistic or aesthetic purposes to its potential as an assistive technology for the visually impaired. I like to think of it as synesthesia: it allows us to experience information in a different modality than it was originally expressed.

There’s no one-size-fits-all way to design a data sonification algorithm—it’s highly dependent on the structure of the data you’re working with and the type of sound you’re trying to create. Since comma-separated values (CSV) are a common way of storing numerical datasets and MIDI is the standard for representing melodic information, it struck me that a tool that could convert between the two formats would come in handy as a generative composition tool. So back in 2018, I made one.

Okinawa, 2017

Sat, 01 Jul 2017 00:00:00 +0000

Shot with a Yashica Electro 35 rangefinder camera around Okinawa, Japan.

Reverse-engineering an RFID writer

Wed, 23 Nov 2016 00:00:00 +0000

I ordered an RFID reader recently for an undergraduate project under the impression it would act like a keyboard emulator, sitting in a waiting state and outputting scanned tags to the keyboard buffer as they came in range. I found, however, that what I bought was actually just a reader/scanner for checking and writing new RFID tags – not for actively scanning them as a check-out station or security system might.