The abolishment of religious censorship brought about a new wave of artistic freedom, resulting in what is known as “La Movida”. All of these are still ever-present issues in Spanish society.įranco’s passing did not just transform Spain politically, but also socially. “La transición” as it’s often referred to, left many wounds open the victims of the Civil War and the post-war years, the impunity many of Franco’s ex-ministers gained and regional tensions to name a few. Of course, things are never so simple – particularly with a country that had such a sordid past. This was a watershed moment for Spaniards, long treated as second class citizens in the continent and one which brought optimism for what the future would bring. Throughout the course of the 1980s, the country did just that – first by being classified as a high income nation by the World Bank in 1982 and joining the European Union in 1986. With the signing of the Constitution in 1978, Spain looked to leave its past behind and to settle in again as a respected West European nation. From 1939 until Franco’s death in 1975, Spain remained somewhat of a pariah on the international stage – an ally the West reluctantly accepted in the Cold War versus the Soviet Union. Once a dominant European power, it had been reduced to a fringe nation mired by poverty and class divisions which eventually culminated in a bloody civil war in 1936. As for AI generated music, I think it will be a travesty to de-value or remove humans from the music/art making process entirely, it will always likely be something derivative of human work in essence anyway, but I don't think it will ever match the depth and soul of human-generated music to people who truly know and love music, some things just can't be emulated.To say the 20 th Century was difficult for Spain may be an understatement. I never thought it would have been possible 20 years ago when I started music. I have been able to remove uncleared vocals from fully mixed tunes that I've made so they can be released as well. It still has a ways to go (as audio quality can be spotty and incomplete), but these online services can often separate more than just vocals now, they can cut individual instruments out of music, and even create pretty good instrumentals. It ended up being the last remix made of his music before his passing, and I sent it to his manager just before, so I'd like to believe he heard it. I used it to remix one of my favorite songs ever by Biz Markie just before he passed last year. One thing that's been pretty interesting is AI vocal splitting, which has revolutionized the art of remixing music that couldn't be fully remixed before. But again - this is probably far from "settled" legally. It was trained on the entire English Spotify catalogue so all that has been digested by the model - under Fair Use. So my understanding is that the training of Jukebox is similar to Copilot. > the data is all locked up behind an impossible quagmire of copyright I tried myself for 6 months, but the processing power required for this is candidly only available for the Google/OpenAIs of the world. Wavenet (from Google) I believe was the first one to do this. This now allows the "subtle" musicalities to be discovered by models without relying on transcription. They break down audio into "blocks" using Fast Fourier Transforms, then each block is "tokenized" and then fed into transformers, similar to GPT-3 or other newer text generation models. What Jukebox (and other models) did well was work with raw audio, rather than rely on MIDI or similar transcriptions. So MIDI songs were being generated quite "early" on, even with basic text generators (LSTM models), where the "alphabet" was replaced by MIDI symbols. But again, music copyright is a pretty complex contraption. The data is all locked up behind an impossible quagmire of copyright.īut if I were a sheet music publishing company, I would be seriously considering the future of music creation with AI given my broad access to notated music & metadata (is this an original score, or a grade 1 simplification?). To me, the former feels much less like AI than the latter. For generative music, we're still largely stuck with encoding musical rules in code rather than feeding data to a transformer. So if you want to automatically create something that sounds like mozart, you're in luck!īut this isn't really satisfying to me. If we had midi transcriptions of 100k songs (abc notation could be fine too), we could probably get really interesting stuff, but most of what is available is lossy chord transcriptions and classical music (public domain). Even something as seemingly simple as chord progressions are very difficult to annotate properly without deep training. Has anyone solved the data problem? I have taken many stabs at this over the last 10 years, and the primary problem is that music is _extremely_ subtle.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |