{"id":7303,"date":"2017-07-06T18:20:43","date_gmt":"2017-07-06T18:20:43","guid":{"rendered":"https:\/\/rsoftsolution.com\/blog\/from-mozard-to-botzard-when-machines-write-our-music.html"},"modified":"2017-07-06T18:20:43","modified_gmt":"2017-07-06T18:20:43","slug":"from-mozard-to-botzard-when-machines-write-our-music","status":"publish","type":"post","link":"https:\/\/www.rbsitsoftwaresolution.in\/blog\/from-mozard-to-botzard-when-machines-write-our-music.html","title":{"rendered":"From Mozard to Botzard: when machines write our music"},"content":{"rendered":"
\n
\n
\n \"music\"<\/a>
\n Credit: CC0 Public Domain
\n <\/figcaption><\/figure>\n

Machines are already taking our jobs, will they soon be writing our music too?\n <\/p>\n


\n <\/section>\n

Swiss researchers said Thursday they have developed a computer algorithm that can generate brand-new tunes in different musical genres.<\/p>\n

The deep artificial composer, or DAC, “can produce complete melodies, with a beginning and an end, that are completely original,” said co-developer Florian Colombo of the EPFL research university in Lausanne, Switzerland.<\/p>\n

And the melodies are “quite agreeable to listen to,” he told AFP.<\/p>\n

The DAC programme uses a form of artificial intelligence known as “deep learning” that works in a similar way to the human brain in memorising experiences and learning from them.<\/p>\n

It is a fast-growing field, with more and more possibilities opening up as computers grow stronger and databases larger.<\/p>\n

The DAC system is trained to “listen” to existing tunes to learn what works and what does not.<\/p>\n

It teaches itself to predict the pitch and duration of every note following another.<\/p>\n

Once it is accurate at predicting 50 percent of note pitches and 80 percent of note durations in existing songs, the machine’s training is complete. <\/p>\n

Then starts the creation. <\/p>\n

<\/figure>\n

“The deep artificial composer builds a string of notes from beginning to end, including the very first note,” said an EPFL statement.<\/p>\n

It picks a follow-up note for each note played, based on the range of probabilities it memorised. <\/p>\n

But the programme is taught not to pick the single-most probable note\u2014rather one of the many between least and most probable.<\/p>\n

Cannot fool them<\/b><\/p>\n

“An algorithm that always opts for most probable note will just keep repeating the same thing,” said Colombo. <\/p>\n

Instead, the programme was designed to produce “an infinity of different tunes”.<\/p>\n

It may be versatile, but the DAC is no Mozart.<\/p>\n

Experts asked to listen to DAC- and human-composed melodies can still tell the difference.<\/p>\n

“It will be a while before an algorithm will fool connoisseurs of Irish folk music,” said Colombo.<\/p>\n

The researchers tested their programme on Irish and Ashkenazi Jewish folk music. The DAC was able to identify the genre, and avoid mixing the two.<\/p>\n

Any musical style can be used, said the team.<\/p>\n

For the moment, the DAC is limited to single-instrument compositions. Eventually, its developers hope it will create a full orchestra score.<\/p>\n

The goal, however, is not to replace flesh-and-blood human composers. <\/p>\n

“It is more a tool that can be used to stimulate creativity, to aid the process of composing” in periods of writer’s block, said Colombo.<\/p>\n

He cited Mozart, who is rumoured to have thrown dice to pick notes.<\/p>\n

DAC-composed music may eventually be used for jingles, but probably never as “serious music<\/a>,” said Colombo.<\/p>\n

“A good composer, with innovative ideas, will never be supplanted by an algorithm,” he said.<\/p>\n

“A composer<\/a> puts something of himself in what he creates, and that a machine cannot do.”<\/p>\n

Several companies, including Google, Sony and IBM are working on similar projects.\n <\/p>\n

\n \"\"
\n Explore further:<\/b>
\n Robot uses deep learning and big data to write and play its own music<\/a>\n <\/p>\n