Artificial Intelligence music maker - artificial-intelligence

Do you know the name of a tool to do some tones from a set of examples, I recently heard it created a great classical song like Bach's.

There has been at least one neural network attempt where the input for the network is music samples, and the output is also music samples. Therefore if the network is trained on Bach, it will output Bach-sounding music. You may be more specifically referring to the Harmonisation of Bach chorales paper:
This project is an attempt to produce intelligent machine harmonisation of
chorales. The goal is to harmonise melodies in the style of J.S.Bach; we wish to
nd tendencies and perhaps rules that Bach may have followed consciously or
unconsciously.
We have chosen a GA approach to construct the new harmonisations. We
discuss the use of rule-based evaluation and proceed to make experiments that
are based on neural net tness evaluation after training on a set of Bach chorales

Here you go:
http://en.wikipedia.org/wiki/David_Cope
http://artsites.ucsc.edu/faculty/cope/

Related

Where to find specification of the jvet/HM and/or the x265 H.265/HEVC encoders?

I'm interested in implementations of H.265/HEVC encoders, which can be used in practice. Since the H.265/HEVC standard only defines the decoder, finding good syntax elements is the job of the encoder. However, I guess finding the optimal syntax elements is infeasible, and thus, I assume that it is up to the designer of the encoder to develop Heuristics in order to determine good enough syntax elements within a reasonable time.
To get an idea how such Heuristics could look like, I had a look at two open source encoders:
jvet/HM: https://vcgit.hhi.fraunhofer.de/jvet/HM
x265 HEVC Encoder: https://bitbucket.org/multicoreware/x265_git/src/master/
However, I cannot find any document that is specifying either of both encoders. By just looking at the source code, it is very hard for me to understand how the Heuristics work.
Does by chance anyone know where I can find these specifications? And/or does anyone know a reasonable implementation of an HEVC encoder with a proper specification?
Thanks a lot!
[I had a look at the repositories jvet/HM (https://vcgit.hhi.fraunhofer.de/jvet/HM) and x265 HEVC Encoder (https://bitbucket.org/multicoreware/x265_git/src/master/) but could not find a document that is specifying the used algorithms. I tried to find other open source encoders but was not successful.]

Is it possible to determine audio shuffle/random code & assess it based on the end user's experience?

Firstly, I am not a programmer. I am an end user who has had some recent home audio experiences that confuse me that i believe are related to the random/shuffle code that the manufacturer installed.
This is an exercise in educating myself & i thought that the programmer community would be a good place to go. I have read a number of random/shuffle threads here & although i don't understand the specifics of the coding discussed, i think i have gained a general understanding of the concepts (& challenges that are faced in writing it).
The issue I've encountered relates to random playback using a 32 Gb USB thumb drive in my new Marantz 6007 single disc CD player (a feature promoted by Marantz in their documentation). Other owners have also raised the issue that i will describe below.
In short, it only plays 'random' songs from Artists whose names begin with a number and those beginning with an A & B (ie. The beginning of the alphabetical listings). This array of songs only amounts to a total of 312 files on my thumb drive. It seems inconceivable that Marantz would specifically write code for that small of an array (or that there is a coding error) especially since it's specs list a maximum permissible thumb drive file content as 65025 files.
FYI:
Skipping forward to the next song in the 'random' sequence does not resolve the issue. Removing folders & sub-folders from the thumb drive such that only song files exist on the drive does not change the results.
My experiences with this feature have been disappointing & baffling from an end user perspective. I can't imagine the the manufacturer's thought processes that would so limit the random play feature.
I look forward to reading your opinions & comments in the hopes of informing myself & preparing myself should i end up in direct coomunication with Marantz (i have not received their response to my online support submission as ofvthis writing). It's a great product save for the issue noted above.
I'm not sure if i've placed this question in the correct location. Nor do i know whether this is even a subject that you want to address in this community given the absence of a specific coding question. I guess that the moderator will decide.
Regardless, i thank you in advance for reading my overlong message & also for any insights you may provide. If you require additional information from me, i'll do my best to provide it in a timely fashion.

how to convert jpegs to video with fixed fps?

I have a series of jpegs,I would like to pack and compress them to a Video.
I use tool mpeg streamclip, but it double the whole play time.
If I have 300 jpegs, set fixed fps 30, I expect to get a video of 10s length . but using stream clip I get a 20s long video.
One answer is to get someone who understands programming. The programming APIs (application interfaces, the way client programs call libraries) to the lig libraries like ffmeg have ways in which frame rate can be controlled, and it's usually quite a simple matter to modify a program to produce fewer intermediate frames if you are creating a video from a list of JPEGs.
But the best answer is probably to find a tool that supports what you want to do. That's not a question to ask a programmer especially. Ask someone who knows about video editing. (It would take me about two days to write such a tool from scratch on top of my own JPEG codec and ffmpeg, so obviously I can't do it in response to this question, but that's roughly the level of work you're looking at).

How to filter specific frequencies from an Audio file in C

After searching on various search engines, and also here, there is very little information applicable to my situation.
Basically I want to make a program in C that does the following:
Open an Audio File (flac Mp3 and wav, to represent a bit of variety)
Filter and cut out a specific set of frequencies (for Example 4000-5200hz, the frequencies should be entered upon inquiry)
Save the new file (without the filtered frequencies) in the same format as the input file.
Things that would be of interest to me:
Open-Source examples of software that does the same or a similar thing, preferably in C
ANY literature on audio programming in C
Explanations on how the different formats are structured, any sources appreciated
Ps.: I apologise if some parts of the question can be easily googled, but I tried, and there wasn't anything that described this well in detail.
Thanks a lot!!
Answers:
FFmpeg does a lot of audio slicing and dicing, and it's written in pure C. It's pretty big, though, and might be difficult to digest in one go.
"Audio programming" is a bit vague. But from the rest of your question, it sounds like you want to open an audio file from disk, apply some transformations to the audio, and write the data to a new file. (Other areas under the "audio programming" umbrella would include accessing platform-specific APIs to read from a microphone and write audio to an output device).
Broad topic again, but we'll start simple.
I suggest getting (or generating) a .WAV file to start with. WAV files are probably the simplest audio files to read and write manually. Here is a page that describes what you need to know about the WAV format.
Pulse code modulation (PCM) is the simplest audio format to work with since you don't need to worry about decompressing it first. Here is a page (that I wrote) describing different PCM formats.
As for filtering and cutting different frequencies, I think what you're looking for would be low-pass, high-pass, or band-pass filters.
I hope that helps you get started. Ask more questions here on Stack Overflow as needed.

how to add controls for a game using batch files?

I am attempting to make a platform game using batch files. I know this seems like a waste of time and there are better tools out there but I just wanted try it out. How do you set up controls so my character moves, jump, gravity and collision? Here's a link to a vid that shows a platform game made in batch file: http://www.youtube.com/watch?v=O_Egqa0Gqhc
You could start with reading Batch Minesweeper and pacman to learn a bit about batch gaming.
But to handle the arrow keys you need always an external program, as choice can't handle them.
With choice you could use "normal" letters, so you could use ASDW to move instead of the arrow keys, but choice is not available in XP.
And you should know how to start and communicate between multiple batch processes.
What you can do is try useing the bscript engine that way you will already the stuff that you need to make ur game but, consider the manual is extreme not like hugh extreme ment a bit confusing and take time to settle . Considering theyre trying to make the engine very fliud in batch script which is hugh lol

Resources