Posts

Showing posts from December, 2018

On the 10th day of Christmas, you'll never guess what my RA gave to me! (🎵Ten Hours of Data🎵)

Image
Introduction In my previous post I showed that SampleRNN seems to perform well with 10-hour datasets. So naturally I wanted to try some more datasets of this length. Experiments Birds The rain dataset from last time produced some nice birdsong. So I found the video shown in Example 1, which contains 10 hours of birdsong. Example 1: Video containing 10 hours of non-repetitious birdsong, used to train SampleRNN. I used that to train SampleRNN for 120&nbsp000 iterations (a day and a half). Some of the results are in Example 2; Example 2: Sounds generated by WaveRNN trained for 120 000 iterations on a 10-hour bird dataset. Fire I found several long recordings of fire sounds on Youtube, shown in Example 3. Example 3: Videos containing a total of 12 hours of fire recordings, used to train SampleRNN. One must be careful when selecting videos from Youtube, because many nominally 10 hour recordings are actually 1 hour of unique aud...

10 ways 10 hours of raindrops can help you live to 100

Image
Introduction I was listening to this stuff generated by SampleRNN. It seems almost unreasonably good compared to some of the results I have been getting. The most obvious difference is that that person is using 30 to 50 hours of training data, as compared to my typical 1 hour. To a certain extent I have been avoiding using huge datasets, because in a way Ambisynth makes more sense if we can use small datasets -- i.e. if you have 50 hours of soundscapes, why synthesize more? So for now, this post represents more of a (forbidden) research question: how good can synthesized soundscapes be; let's assume practical considerations will take care of themselves at some point in the future. Dataset So I made a 10.5-hour dataset with audio from this amazing website (it's well worth a good listen): https://recordingsofnature.wordpress.com . The recordings were all made with stereo microphones attached to trees in the woods near lakes between 3 and 5 in the morning. I chose several f...

It's just the beasts under your bed, in your closet, in your head

Image
It's the future. The Exciting Future Of Technology. Tomorrow. Innovation. Science. As long as I have this thing on my face I can't even see the past. I want to have my natural senses revoked. And replaced by car adverts if possible. This is definitely going to make everybody's life better. EverybodysLife™ Here, put this big pacifier in your mouth and stop asking questions. My vision of the future is probably universal, so maybe I should keep trying to make it everybody's future.