Tag: Bad Snacks

Lo-Fi Star Bad Snacks Drops Spotify Singles and Helps You Create Your Own

June 15, 2023

Beautiful music should be shared. From the studio to the stage, producer Bad Snacks embodies that philosophy, creating music that resonates with global audiences and gets them moving. Throughout her career, she’s never hesitated to give fellow artists a look into her process.

Rich with lo-fi and dance influences, Bad Snacks’s catalog of songs offers up a soundscape of lush strings, driving basslines, and hard-hitting grooves. After going viral on Andrew Huang’s “4 Producers” challenge, she released several instrumental beat tapes that garnered an overwhelmingly enthusiastic response, amassing millions of streams. Her dedication to fans and for other creators to explore their creativity remains unwavering as she unveils a sound pack with Soundtrap featuring 28 loops and 52 one-shots to help take your lo-fi production game to the next level. 

Soundtrap is an online studio for songwriters and beat makers. Made by musicians and producers, Soundtrap offers an intuitive interface, coupled with over 24,000 royalty-free loops and instruments, to make professional-sounding music and storytelling simple and collaborative for everyone, no matter where they are. 

The Bad Snacks collaboration, available on the Music Maker Supreme and Complete plans, is the latest addition to the expansive Soundtrap Originals series, a biweekly release of audio content produced by a network of music producers exclusively for Soundtrap users. The sound pack contains handpicked ingredients straight from Spotify’s Studio in LA, produced by Bad Snacks just for Soundtrap. It’s full of lush, vintage textures, spicy drums recorded from historical synths, classic 808s, and some fresh strings from Bad Snacks’s 100-year-old violin.

Want to cook up some tracks yourself? Try Soundtrap now.

Recently, we also invited the producer to step into our Spotify Studios in LA to work with a number of talented engineers and musicians to create her own samples and then use them in a pair of new Spotify Singles—the dreamy, nostalgic reimagining of the New Radicals hit “You Get What You Give,” as well as an original track, the ethereal, lo-fi beat-heavy “Technicolor.”

For the Record caught up with Bad Snacks to talk about the new sound pack, her new Spotify Singles, and what it was like to geek out in Spotify Studios. 

Tell us about the creative approach to your tracks for Spotify Singles. 

Although I started as a lo-fi producer, I think a major part of my sound and evolution has been about incorporating sounds beyond lo-fi while maintaining those warm-hug mushy feelings that lo-fi evokes. For my Spotify Singles, I really felt like the way to evolve lo-fi was to curate the samples I use as much as possible, which is why I enlisted the help of my friend, arranger Ryan Reeson, harpist Nailah Hunter, and Wholesoul. We were able to use Spotify Studios to record a string quartet and harp piece that took a lot of cues from golden-era Hollywood compositions, and then I was able to slice those into an instrumental that felt very genuine to me.

How did recording at Spotify Studios differ from your everyday production and practices? 

Spotify Studios is a wonderland for someone like myself. It’s not very often that I get access to such a nice studio with all-star musicians and recording engineers, so I definitely wanted to take advantage of that. Usually my everyday production practices include a lot of messing around and experimentation, but this session was extremely premeditated and thoughtfully planned since we had so many logistics to organize. 

There’s an unbelievable amount of cool, unique, and well-loved gear that all have deep stories behind them. Like, coming across a single-generation bass synth made by a water heater company? Crazy! It didn’t take long for me to start geeking out with the studio engineers about every fun fact in that room.

What tools do you use to create your music?

I’m a huge synth nerd, so I really use anything that I can experiment with. At Spotify Studios, it was such a treat to work with familiar—and unfamiliar!—gear. Especially Roland’s Juno-104 and TR-808 synths, and Hologram’s Microcosm pedal. Of course, I’m also a string player, so my violin is extremely instrumental to almost every track I make. 

And of course Soundtrap is super neat because it’s very accessible, and the way it makes real-time online collaborating possible is very helpful.

You recently released a sound pack on Soundtrap that users can use for their own music. Why is it important for artists to be able to share resources and skills with one another?

We’re in a really unprecedented age of idea sharing in the arts community. As a self-taught producer and engineer, I can’t express how helpful it is to have access to some of the same ingredients that my favorite producers cook with. I have always been pretty open with my processes and resources, and although I don’t believe that should be an expectation of producers and artists, I know that being transparent and generous has surrounded me with a community that has benefited me in multitudes. 

And as a producer, I’m always on the hunt for sample packs to get the ideas flowing. So with this current pack, I wanted to create sounds that are not only very usable, but could inspire producers in potentially unexpected ways. I hope people enjoy these vintage textures, because it was such a blast to create them.

Who are some of your biggest creative influences? 

This is always a tough question because there are always so many, and they also shift with the seasons. Some of my all-time favorites are Flying Lotus, Björk, TOKiMONSTA, Radiohead, Teebs, and Disclosure. They all have catalogs that I never get tired of.

Hear ‌the fruits of Bad Snacks’s labor in Spotify Studios on her two Spotify Singles below:

Rachel Bittner on Basic Pitch: An Open Source Tool for Musicians

September 1, 2022

orange open source and coding symbols on a blue, green, and white background

Music creation has never been as accessible as it is now. Gone are the days of classical composers, sheet music, and prohibitively expensive studio time when only trained, bankrolled musicians had the opportunity to transcribe notes onto a page. As technology has changed, so too has the art of music creation—and today it is easier than ever for experts and novices alike to compose, produce, and distribute music. 

Now, musicians use a computer-based digital standard called MIDI (pronounced “MID-ee”). MIDI acts like sheet music for computers, describing which notes are played and when—in a format that’s easy to edit. But creating music from scratch, even using MIDI, can still be very tedious. If you play piano and have a MIDI keyboard, you can create MIDI by playing. But if you don’t, you must create it manually: note by note, click by click. 

To help solve this problem, Spotify’s machine learning experts trained a neural network to predict MIDI note events when given audio input. The network is packaged in a tool called Basic Pitch, which we just released as an open source project. 

“Basic Pitch makes it easier for musicians to create MIDI from acoustic instruments—for example, by singing their ideas,” says Rachel Bittner, a research manager at Spotify who is focused on applied machine learning on audio. “It can also give musicians a quick ‘starting point’ transcription instead of having to write down everything manually, saving them time and resources. Basically, it allows musicians to compose on the instrument they want to compose on. They can jam on their ukulele, record it on their phone, then use Basic Pitch to turn that recording into MIDI. So we’ve made MIDI, this standard that’s been around for decades, more accessible to more creators. We hope this saves them time and effort while also allowing them to be more expressive and spontaneous.”

For the Record asked Rachel to tell us more about the thinking and development that go into Basic Pitch and other machine learning efforts, and how the team decided to open up the tool for anyone to access and to innovate on.

Help us understand the basics. How are machine learning models being applied to audio?

Rachel Bittner

On the audio ML (machine learning) teams at Spotify, we build neural networks—like the ones that are used to recognize images or understand language—but ours are designed specifically for audio. Similar to how you ask your voice assistant to identify the words you’re saying and also make sense of the meaning behind those words, we’re using neural networks to understand and process audio in music and podcasts. This work combines our ML research and practices with domain knowledge about audio—understanding the fundamentals of how music works, like pitch, tone, tempo, the frequencies of different instruments, and more.

What are some examples of machine learning projects you’re working on that align with our mission to give “a million creators the opportunity to live off their art”?

Spotify enables creators to reach listeners and listeners to discover new creators. A lot of our work helps with this in indirect ways—for example, identifying tracks that might go well together on a playlist because they share similar sonic qualities like instrumentation or recording style. Maybe one track is already a listener’s favorite and the other one is something new they might like.

We also build tools that help creative artists actually create. Some of our tech is in Soundtrap, Spotify’s digital audio workstation (DAW), which is used to produce music and podcasts. It’s like having a complete studio online. And then there’s Basic Pitch, which is a stand-alone tool for converting audio into MIDI that we just released as an open source project. We open sourced Basic Pitch and built an online demo, so anyone can use it to translate musical notes in a recording (including voice, guitar, or piano).

Unlike similar ML models, Basic Pitch is not only versatile and accurate at doing this, but it’s also fast and computationally lightweight. So the musician doesn’t have to sit around forever waiting for their recording to process. And on the technological and environmental side, it uses way less energy—we’re talking orders of magnitude less—compared to other ML models. We named the project Basic Pitch because it can also detect pitch bends in the notes, which is a particularly tricky problem for this kind of model. But also because the model itself is so lightweight and fast.

What else makes Basic Pitch a unique machine learning project for Spotify?

I mentioned before how computationally lightweight it is—that’s a good thing. In my opinion, the ML industry tends to overlook the environmental and energy impact of their models. Usually with ML models like this—whether it’s for processing images, audio, or text—you throw as much processing power as you can at the problem as the default method for reaching some level of accuracy. But from the beginning, we had a different approach in mind: We wanted to see if we could build a model that was both accurate and efficient, and if you have that mindset from the start, it changes the technical decisions you make in how you build the model. Not only is our model as accurate as (or even more accurate than) similar models, but since it’s lightweight, it’s also faster, which is better for the user, too. 

What’s the benefit of open sourcing this tool?

It gives more people access to it since anyone with a web browser can use the online demo. Plus, we believe the external contributions from the open source community help it evolve as software to create a better, more useful product for everyone. For example, while we believe Basic Pitch solves an important problem, the quality of the MIDI that our system (and others’) produces is still far from human-level accuracy. By making it available to creators and developers, we can use our individual knowledge and experience with the product to continue to improve that quality. 

What’s next for Basic Pitch in this area?

There’s so much potential for what we can do with this technology in the future. For example, Basic Pitch could eventually be integrated into a real-time system, allowing a live performance to be automatically accompanied by other MIDI instruments that “react” to what the performer is doing.

Additionally, we shared an early version of Basic Pitch with Bad Snacks, an artist-producer who has a YouTube channel where she shares production tips with other musicians. She’s been playing around with Basic Pitch, and we’ve already made improvements to it based on her feedback, fixing how the online demo handles MIDI tempo, and other things to make it work better for a musician’s workflow. We partnered with her to use Basic Pitch to create an original composition, which she released as a single on Spotify. She even posted a behind-the-scenes video on her channel showing how she used Basic Pitch to create the track. The violin solo section is particularly cool.

But it’s not just artists and creators that we’re excited about. We’re equally looking forward to seeing what everyone in the open-source developer community has been doing with it. We expect to discover many areas for improvement, along with new possibilities for how it could be used. We’re proud of the research that went into Basic Pitch and we’re happy to show it off. We’ll be even happier if musicians start using it as part of their creative workflows. Share your compositions with us!

Create a cool track using Basic Pitch? Share it on Twitter with the hashtag #basicpitch and tag the team @SpotifyEng.