SomethingUnreal | Animecon 2011: R/C Yukkuri "Yumekuri" Compilation (incomplete edit) [HD] @SomethingUnreal | Uploaded 13 years ago | Updated 6 hours ago
Just a few clips of Dnstje's remote-controlled yukkuri at Animecon in the Netherlands last weekend. It never fails to entertain. This time, he made a Yumekui Merry (Merry Nightmare) hat for it, making it a yumekuri!

(Is comedic swearing in Dutch safe on YouTube? xD)

Apologies for the incomplete editing - this was not originally going to be the final edit, but my computer's CPU died (of all things), and I'm not able to continue editing using my netbook. This was just going to be a test render, but since I won't have any money to get my computer up and running again for about a month, I'm uploading the video now in its incomplete state.

~Shining In The Sky~ (Clannad OST) on Bawami [rev 93] [HD]

Gekiryuu Sanzu Kawa (Komachis Theme remix) - Bleeper-Style

[Touhou] Bad Apple!! Remake with Live Playing [HD]

[MIDI] Behind Closed Doors (Live In Arcadia) [SC-88Pro]

[MIDI] Prince Of The Yolkfolk (DOS version) [SC-88Pro]

Computer-controlled singing motor - 2nd Video

$Neural Network Tries to Generate English Speech (RNN/LSTM) By popular demand, I threw my own voice into a neural network (3 times) and got it to recreate what it had learned along the way! This is 3 different recurrent neural networks (LSTM type) trying to find patterns in raw audio and reproduce them as well as they can. The networks are quite small considering the complexity of the data. I recorded 3 different vocal sessions as training data for the network, trying to get more impressive results out of the network each time. The audio is 8-bit and a low sample rate because sound files get very big very quickly, making the training of the network take a very long time. Well over 300 hours of training in total went into the experiments with my voice that led to this video. The graphs are created from log files made during training, and show the progress that it was making leading up to immediately before the audio that you hear at every point in the video. Their scrolling speeds up at points where I only show a short sample of the sound, because I wanted to dedicated more time to the more impressive parts. I included a lot of information in the video itself where its relevant (and at the end), especially details about each of the 3 neural networks at the beginning of each of the 3 sections, so please be sure to check that if youd like more details. Im less happy with the results this time around than in my last RNN+voice video (https://www.youtube.com/watch?v=FsVSZpoUdSU), because Ive experimented much less with my own voice than I have with higher-pitched voices from various games and havent found the ideal combination of settings yet. Thats because I dont really want to hear the sound of my own voice, but so many people commented on my old video that they wanted to hear a neural network trained on a male English voice, so here we are now! Also, learning from a low-pitched voice is not as easy as with a high-pitched voice, for reasons explained in the first part of the video (basically, the most fundamental patterns are longer with a low-pitched voice). The neural network software is the open-source torch-rnn (https://github.com/jcjohnson/torch-rnn/), although that is only designed to learn from plain text. Frankly, Im still amazed at what a good job it does of learning from raw audio, with many overlapping patterns over longer timeframes than text. I made a program(*) that substitutes raw bytes in any file (e.g. audio) for valid UTF-8 text characters and torch-rnn happily learned from it. My program also substituted torch-rnns generated text back into raw bytes to get audio again. I do not understand the mathematics and low-level algorithms that go make a neural network work, and I cannot program my own, so please check the code and .md files at torch-rnns Github page for details. Also, torch-rnn is actually a more-efficient fork of an earlier software called char-rnn (https://github.com/karpathy/char-rnn), whose project page also has a lot of useful information. I will probably soon release the program that I wrote to create the line graphs from CSV files. It can make images up to 16383 pixels wide/tall with customisable colours, from CSV files with hundreds of thousands of lines, in a few seconds. All free software I could find failed hideously at this (e.g. OpenOffice Calc took over a minute to refresh the screen with only a fraction of that many lines, during which time it stopped responding; the lines overlapped in an ugly way that meant you couldnt even see the average value; and exporting graphs is limited to pressing Print Screen, so youre limited to the width of your screen... really?). (*)Here is the code rewritten from VB6 in a C++-like pseudocode: http://robbi-985.homeip.net/information/bintoutf8_pseudo.txt Also, here is an English explanation of the idea behind how it works: http://robbi-985.homeip.net/information/bintoutf8_info.txt EDIT: I have released my BinToUTF8 program to the public! Please have a look here: http://robbi-985.homeip.net/blog/?p=1845$

Model aircraft nitro engine, computer-controlled

Computer-Controlled Toy Washing Machine (behind the scenes)

Animecon 2011: R/C Yukkuri "Yumekuri" Compilation (incomplete edit) [HD] @SomethingUnreal