Another possibly-too-deep dive from me! I took a week off from work recently to reimplement Storyteller's forced alignment algorithm. Storyteller is an open source, self hosted platform for...
Another possibly-too-deep dive from me! I took a week off from work recently to reimplement Storyteller's forced alignment algorithm. Storyteller is an open source, self hosted platform for creating, managing, and reading/listening to "readaloud" books — books that have audiobook narration built in and can highlight each sentence (and/or word, with this new algorithm!) as it's read aloud. Forced alignment is the process of determining where each piece of text starts and ends in the audiobook.
Anyway, I am really pleased with how the new algorithm turned out! Hopefully someone else finds it interesting as well.
A very enjoyable read! The animated/stepped diagrams were very helpful. Though I have to say, "forced alignment"is a pretty ominous name for an otherwise interesting and useful tool.
A very enjoyable read! The animated/stepped diagrams were very helpful. Though I have to say, "forced alignment"is a pretty ominous name for an otherwise interesting and useful tool.
Thanks! I put a lot of time into those graphics — the piece felt very hard to follow without them I think. I'm glad to hear they were helpful! Yeah I "forced alignment" is the technical term — it...
Thanks! I put a lot of time into those graphics — the piece felt very hard to follow without them I think. I'm glad to hear they were helpful!
Yeah I "forced alignment" is the technical term — it has always felt very... aggressive? to me. :shrug:
Did you know that Max Fleischer invented the "follow the bouncing ball" technique in 1924 for this animated short films? 'Follow the bouncing ball' is not quite technical sounding but it does have...
Did you know that Max Fleischer invented the "follow the bouncing ball" technique in 1924 for this animated short films? 'Follow the bouncing ball' is not quite technical sounding but it does have an intuitive and well-defined meaning.
No I did not, thanks for sharing! This is a handy bit of trivia for the endless hordes of folks that love to jump into every thread about Storyteller and bemoan "modern attention spans". Super...
No I did not, thanks for sharing! This is a handy bit of trivia for the endless hordes of folks that love to jump into every thread about Storyteller and bemoan "modern attention spans". Super interesting!
Another possibly-too-deep dive from me! I took a week off from work recently to reimplement Storyteller's forced alignment algorithm. Storyteller is an open source, self hosted platform for creating, managing, and reading/listening to "readaloud" books — books that have audiobook narration built in and can highlight each sentence (and/or word, with this new algorithm!) as it's read aloud. Forced alignment is the process of determining where each piece of text starts and ends in the audiobook.
Anyway, I am really pleased with how the new algorithm turned out! Hopefully someone else finds it interesting as well.
A very enjoyable read! The animated/stepped diagrams were very helpful. Though I have to say, "forced alignment"is a pretty ominous name for an otherwise interesting and useful tool.
Thanks! I put a lot of time into those graphics — the piece felt very hard to follow without them I think. I'm glad to hear they were helpful!
Yeah I "forced alignment" is the technical term — it has always felt very... aggressive? to me. :shrug:
Did you know that Max Fleischer invented the "follow the bouncing ball" technique in 1924 for this animated short films? 'Follow the bouncing ball' is not quite technical sounding but it does have an intuitive and well-defined meaning.
You might find this article interesting: https://www.nydailynews.com/2005/04/12/point-man-max-fleischer-and-the-bouncing-ball/
No I did not, thanks for sharing! This is a handy bit of trivia for the endless hordes of folks that love to jump into every thread about Storyteller and bemoan "modern attention spans". Super interesting!