Unlock Your Audio Processing Superpowers With Rest API - Baptiste Vericel & Alexandre Louiset - ADC 2023
For any audio feature you need to implement in your product, API integration will grant you limitless capabilities, with numerous advantages (low code, fast deployment, scalable). During this talk we'll highlight the key concepts of Rest APIs for audio processing, its relevancy and benefits for any type of audio software and app development workflows, through a groundbreaking demo, showcasing best-in-class technologies straight from IRCAM lab we’re aiming at making accessible.
_
Baptiste Vericel
With a background in acoustics and signal processing (ENSEA, IRCAM), he has worked with a number of companies (Arkamys, Devialet) for more than a decade as a signal processing and electroacoustics engineer. Passionate about audio and live music, he set up his own podcasting company.
_
Alexandre Louiset
Alexandre is on a mission to make the IRCAM sound research technology resonate and unlock new territories for the pro audio community.
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Join Us For ADC24 - Bristol - 11-13 November 2024
More Info: https://audio.dev/
@audiodevcon​
Music Hack Day India Winner Presentations - - ADC 2023
Music Hack Day India is a gathering of researchers, developers, creative coders, musicians, makers, engineers, audiophiles and more. It was hosted on 5th & 6th Jan 2024, preceding ADCx India and included many interesting hacks from the participants.
The winners of the hackathon were invited to present their idea on the ADCx India platform.
Inspira - A Tool for Musical Inspiration
Chordeezy - Complex chord generation made simple
Fly by Ear - An Audio Game Accessible to People with Visual Impairments
Singing Synthesis Beyond Human-Level Naturalness: Not What You Think - Kanru Hua - ADC 2023
Achieving human-level naturalness is often viewed as the pinnacle of vocal synthesis research. While recent advances in Text-to-Speech (TTS) using deep generative models has reported subjective ratings comparable to human speech, singing synthesis hasn't reached this milestone. In this presentation, we showcase a singing synthesis system that, intriguingly, exceeds raw recordings in comparative mean opinion score tests—with statistical significance. However, as we delve deeper, we highlight the subtle but crucial differences between true human parity and competitive ratings in subjective tests, challenging our understanding of “naturalness” in this domain. We will also unpack the complexities of subjective quality evaluation, the unique challenges posed by singing versus speech, and shed light on the implications these findings hold for future designs of singing synthesis systems.
Link to Slides:
_
Kanru Hua
Kanru Hua founded Dreamtonics (developer of Synthesizer V) in 2019, after dropping out of University of Illinois. A self-taught programmer and researcher, Kanru has been focusing on bridging speech signal processing algorithms with the latest advances in generative models, as well as addressing the production challenges of deploying neural networks for audio processing. He was nominated for Forbes JAPAN 30 UNDER 30 in 2022.
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Join Us For ADC24 - Bristol - 11-13 November 2024
More Info: https://audio.dev/
@audiodevcon​
Diversity in Music Technology: Diversity Initiatives and Insights From Music Information Retrieval - Blair Kaneshiro - ADC23
Like many STEM fields, music technology faces challenges attracting and retaining diverse community members. Since 2011, the International Society for Music Information Retrieval (ISMIR) and Women in Music Information Retrieval (WiMIR) communities have sought to address this issue through a series of initiatives – ranging from financial support to attend ISMIR conferences to workshop events and mentorship – that were launched to promote opportunities for women in the field. In this talk I will discuss the initiatives: Their motivation and formation, complementary aims, success factors, and evolution toward supporting a broader range of underrepresented groups. I will conclude with a set of insights that may inform the design of diversity initiatives in other music technology communities.
Link to Slides: https://data.audio.dev/talks/2023/diversity-in-music-technology/slides.pdf
_
Blair Kaneshiro
Director of Research & Development, Stanford University
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Join Us For ADC24 - Bristol - 11-13 November 2024
More Info: https://audio.dev/
@audiodevcon​
ORCA Livecoding Soundscape for Theatre - Padmanabhan J - ADCx India 2024
ORCA, an esoteric language developed by Hundred Rabbits, provides a dynamic live coding environment for users to spontaneously create generative music. This programming tool operates within the realm of a base-36 system, accompanied by 8 distinct special character functions, making it accessible and adaptable for coders and musicians alike. The design and underlying philosophy behind ORCA open new horizons in exploring programming languages as a compelling alternative to traditional musical notation and composition. In this presentation, we delve into the intriguing world of ORCA, its principles, and its potential to reshape how we conceive and create music.
_
Edited by Digital Medium Ltd - online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC24 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Prashant Mishra
Collaborative Songwriting and Production With Symbolic Generative AI - Sadie Allen & Anirudh Mani - ADC23
Generative AI has experienced remarkable advancements in various domains, including audio and music. However, despite these breakthroughs, we have yet to reach a stage where musicians can seamlessly incorporate generative AI into their creative processes. In this talk, we will delve into the techniques, proposals, and ongoing work that can facilitate collaborative songwriting and production with machine learning.
During the session, we will explore several key topics:
• Overview of existing tools and models - we will discuss the motivations behind symbolic generation versus raw audio for music production applications. Furthermore, we will highlight the contrasting approaches and techniques that aim to augment the creative process rather than replace it entirely.
• Utilization of AI-generated MIDI as a songwriting tool - this will involve examining different ML architectures for conditional MIDI generation, as well as employing reinforcement learning (RL) to generate MIDI sequences.
• Examples showcasing how speakers and other musicians currently utilize AI-generated MIDI as part of their songwriting/production process.
Attendees will gain insights into cutting-edge techniques and research, paving the way for a future where generative AI becomes an integral part of the creative process for musicians.
Link to Slides: https://drive.google.com/file/d/15qYW-SbgmodMZ_wiMKKvH8pXmrDCZQpY/view?usp=sharing
_
Sadie Allen
_
Anirudh Mani
I build creative AI tools for artists.I am the co-founder of Lemonaide Music. https://www.lemonaide.ai/ https://www.linkedin.com/in/anirudh-mani-1796934b/ https://twitter.com/anirudh3
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Vars, Values and ValueTrees: State Management in JUCE - Jelle Bakker - ADC 2023
Managing various types of state, including global settings, presets, UI state, and application state, is crucial for building robust software. But, it comes with a challenge. State must be synchronized throughout the app. State must be stored and restored. And state is everywhere. There seems to be a lot of debate about what the best way is to solve these problems. The concept of centering your app around a model, a single point of truth, has long been recognized as a powerful pattern, often referred to in the context of MVC (Model-View-Controller). Adopting this approach will make extending and maintaining your software simpler. In JUCE you will find many classes designed for dealing with state, such as the AudioProcessorValueTreeState, ApplicationProperties, Value and Vars. This talk will serve as a guide and overview for how to manage data in JUCE applications.
Link to Slides: https://data.audio.dev/talks/2023/vars-values-and-value-trees/slides.pdf
_
Jelle Bakker
Jelle Bakker is a JUCE developer, building audio-plugins and desktop applications. Jelle has worked as a contract software engineer for different companies across the globe. He specializes in software design and architecture. Besides that, Jelle is a father, coffee lover, and music performer, playing piano, electric guitar and cello.
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Join Us For ADC24 - Bristol - 11-13 November 2024
More Info: https://audio.dev/
@audiodevcon​
Using Convolution for Archeo-Acoustic Conservation - Akash Sharma - ADCx India 2024
Every space has its unique acoustic properties because of the combination of its dimensions, architectural design and use of construction materials. Time over centuries has enriched and created an invigorating experience of space which now is part of our heritage; all our sensory realms have fused into this memorable image of space. We can use computation to determine this unique acoustic property.
_
Edited by Digital Medium Ltd - online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC24 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Prashant Mishra
How to Write Bug-Free, Real-Time Audio C++ Code? - Jan Wilczek - ADC 2023
How many times have we compiled our audio plugin or app and launched it only to find out that "something is glitching"?
How can we be sure that we submit a correctly implemented audio feature in a pull request?
And how can we detect existing problems and precisely locate them in our codebase?
I've been pursuing the answers to these questions from my day 1 in the audio industry and in this talk I am going to share with you my personal favorites. This is not just from my experience; I've actively asked community members for their strategies at every opportunity I got. This is a collected wisdom of more than just a single developer.
In the talk, I will:
1. Outline why shipping bug-free code is vital for your business and your own sanity
2. show you simple yet profound strategies for ensuring software correctness based on digital signal processing (DSP), including:
1. taking advantage of phase cancellation properties
2. leveraging the power of the FFT for frequency-manipulation algorithms,
3. underused DSP tools like total harmonic distortion (THD), Farina sweep, and pole-zero plot,
4. discovering the power of reference audio renders.
3. explain how to safely reuse stable and tested DSP code of other developers,
4. interoperate C++ and Python for accessing powerful numerical libraries and testing complicated scenarios
5. correctly implement even the most advanced DSP algorithms and optimizations,
6. show real-world examples where these principles helped solve hidden audio bugs, including
1. pitch tracking,
2. pitch shifting, and
3. the flanger effect.
With this knowledge you'll be able to:
1. approach developing new features with greater confidence,
2. enjoy more inner peace during development, review, and deployment,
3.write correct audio code every time!
_
Jan Wilczek
Jan Wilczek graduated with honors from Friedrich-Alexander-Universität Erlangen-Nürnberg, having completed a master’s program Advanced Signal Processing and Communications Engineering. He is an Audio Developer of Music Maker JAM at Loudly GmbH in Berlin; an app to make loop-based music that runs on Android, iOS, and Windows.Additionally, he has created TheWolfSound.com to help students and software engineers learn audio programming for getting game audio, audio plugin, or mobile audio developer jobs. He is the author of DSP Pro: an online course on the basics of digital audio signal processing for aspiring audio programmers. He helps others through online courses, one-on-one coaching and publishing tutorials and explainer videos about various aspects of audio programming. Parallel to the educational services, he is a consultant in the field of audio programming. He is also a researcher in the area of Virtual Analog modeling using deep learning; his latest work was presented at the Digital Audio FX 2022 conference in Vienna. His professional goal is to lower the entry barrier for everyone interested in writing audio software. He pursues it by publishing high-quality articles, videos, and podcasts or giving talks.
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
Join Us For ADC24 - Bristol - 11-13 November 2024
More Info: https://audio.dev/
@audiodevcon​
Virtual Acoustics: Recreating Natural Phenomena in the Digital Domain - Aidan Baker - ADC 2023
Audio in the VR / AR domain may become a dominant section of this industry in the coming years. While methods for processing spatial audio already exist (and formal standards have been created and utilized) another factor of immersive audio remains (mostly) untouched: Virtual acoustic systems that mimic the virtual spaces.
This talk will go over various techniques for handling room acoustics in both real-time and offline settings, and going over both their benefits, as well as their drawbacks. Additionally, we will look over how to go about approximating room acoustics without breaking the proverbial (cpu) bank.
_
Aidan Baker
I am an audio developer who is fascinated by sound's physical phenomena. Presently I run a company called Lese which develops audio plugins + acoustic simulation software.
_
Streamed & Edited by Digital Medium Ltd: https://online.digital-medium.co.uk
_
Organized and produced by JUCE: https://juce.com/
_
Special thanks to the ADC23 Team:
Sophie Carus
Derek Heimlich
Andrew Kirk
Bobby Lombardi
Tom Poole
Ralph Richbourg
Jim Roper
Jonathan Roper
Prashant Mishra
