This week, Google researchers published a paper describing the results of a artificial intelligence (AI) tool created to create music.
The tool, called MusicLM, is not the first AI music tool to be released. But the examples that Google provides demonstrate musical creative ability based on a limited set of descriptive words.
AI shows how complex computer systems have been trained to behave in a similar way to humans.
tools like ChatGPT You can quickly produce or generate written documents that compare well with the work of humans. ChatGPT and similar systems require powerful computers to operate complex machine learning models. The San Francisco-based company open AI launched ChatGPT late last year.
Developers train these systems on vast amounts of data to learn methods to recreate different forms of content. For example, computer generated content could include written material, design elements, art, or music.
ChatGPT has recently received a lot of attention for its ability to generate complex writings and other content from a simple description in natural language.
MusicLM by Google
google engineers explain the MusicLM system like this:
First, the user comes up with a word or words that describe the type of music they want the tool to create.
For example, a user might enter this short phrase into the system: “continuous calming violin backed by a soft guitar sound.” Descriptions entered may include different music stylesinstruments or other existing sounds.
several different music examples produced by MusicLM were posted online. Some of the music generated came from one- or two-word descriptions, such as “jazz,” “rock,” or “techno.” The system created other examples from more detailed descriptions that contained complete sentences.
In one example, Google researchers include these instructions to MusicLM: “The main soundtrack of a arcade match. It’s fast paced and optimistic, with a catchy electric guitar riff. music is repetitive and easy to remember, but with unexpected sounds…”
In the resulting recording, the music seems to hold very close to the description. The team said that the more detailed the description, the better the system can try to produce it.
The MusicLM model works in a similar way to the machine learning systems used by ChatGPT. Such tools can produce human-like results because they are trained on large amounts of data. Many different materials are fed into the systems to enable them to learn complex skills to create realistic works.
In addition to generating new music from written descriptions, the team said the system can also create examples based on a person’s singing. buzzerwhistling or playing an instrument.
The researchers said the tool “produces high-quality music…for several minutes, while faithful to the text conditioning signal.”
At this time, the Google team has not released the MusicLM models for public use. This differs from ChatGPT, which became available online for users to experience in November.
However, Google announced that it was releasing a “high-quality data set” of more than 5,500 musical composition pairs prepared by professional musicians called MusicCaps. The researchers took that step to help in the development of other AI music generators.
MusicLM researchers said they believe they have designed a new tool to help anyone quickly and easily create high-quality music selections. However, the team said that it also acknowledges some risks related to the machine learning process.
One of the biggest problems the researchers identified was “bias present in the training data.” A bias could include too much of one side and not enough of the other. The researchers said this raises a question “about chance for the generation of music for cultures underrepresented in the training data”.
The team said it plans to continue studying the results of the system that could be considered cultural appropriation. The goal would be to limit bias through further development and testing.
In addition, the researchers said they plan to further improve the system to include lyrics generation, text conditioning, and better voice and music quality.
I’m Bryan Lynn.
Bryan Lynn wrote this story for VOA Learning English, based on Google reports.
words in this story
artificial intelligence – north the development of computer systems that have the ability to perform work that normally requires human intelligence
style -north. a particular shape or design, usually used to compare forms of art or handiwork
instruction -north. a description of how to do something
arcade – north an area containing many electronic and coin-operated games
optimistic – adj. full of hope and happiness
repetitive – adj. say or do something over and over again
hum – v. make a musical sound without opening your mouth
whistle – v. make a loud sound by forcing air through a small hole in the mouth
faithful – adj. stand firm on an idea or belief
suitable – adj. the level at which something is right for a situation
cultural appropriation – north. when members of one culture in a society, often the main culture, use a practice from another, often minority culture, without fully understanding the meaning or significance of the practice.
What do you think about this story? We want to hear from you. We have a new comment system. Is that how it works:
- Write your comment in the box.
- Below the box, you can see four images for social media accounts. They are for Disqus, Facebook, Twitter and Google.
- Click on an image and a box will appear. Enter the login for your social media account. Or you can create one on the Disqus system. It’s the blue circle with a “D” on it. It’s free.
Each time you comment back on the Learning English site, you can use your account and view your comments and responses to them. Our comment policy is here.
#Googles #artificial #intelligence #tool #creates #music #written #descriptions