Reading research papers takes a lot of time. On top of that, I personally prefer to consume content through audio + video rather than through reading alone.
To make it easier to read more papers, I'm doing an experiment where I make videos that show the full text of a research paper, images as well as reads the paper out loud.
- Prefer to learn through hearing rather than reading alone.
- Like to take a first-pass through a paper while commuting.
- Spend long days staring at a screen and want to give your eyes a rest, lay back and hear a research paper at the end of the day.
- Have a backlog of research papers to read and would like to catch up by reading some of them more casually.
- Want to take a first-pass through a paper before deciding if it’s worth sitting down and working through the details.
How it works:
The videos are a combination of manual video editing and automated generation to make it easier to create. The key is using a cloud-based text to speech engine for reading out the full text. I find most text to speech voices pretty annoying but after some experimentation, I've found that using Google's WaveNet non-real-time cloud-based text to speech has the best sounding voice. I was pleasantly surprised to find a voice I enjoy hearing. (Full disclosure: I work at Google, but I have nothing to do with their text to speech offering nor Google cloud. This is just my personal opinion after testing out several different text to speech engines).
You can find all videos at this YouTube channel. Here's a sample of what's on there:
I tend to post papers I’m interested in, but if you have a paper you’d like me to generate a video for just send me a message on twitter at https://twitter.com/marcsto or email me at firstname.lastname@example.org and I should be able to help