Politicians, by trade, speak often and at length. But the news cycle moves fast, and many words are quickly forgotten, or impossible to recover from hours of broadly labeled footage. That’s where we come in: rather than sift through hours of CSPAN video to research what’s been said about a policy, a search in Pop Up Archive takes you to the exact timestamped point of the relevant discussion.
We’re processing audio for a number of news syndicates. Here are some news collections where you can search political keywords from the public archive:
While we’ve got you covered for radio news, what if you’re looking to search TV news? Thanks to a project from our friends at the Internet Archive, television news footage is more accessible than ever through the TV News Archive. They take media which has already been captioned and make that text searchable to the second.
The age of passive political listening is past. With these tools, you can zone in on your favorite issue with unprecedented acuity.
What is this “Radio Race,” and what does Pop Up Archive have to do with it?
This Saturday, KCRW’s Independent Producer Project is hosting its 2nd Annual Radio Race:
KCRW’s 24-Hour Radio Race is a whirlwind day of high-stakes radio making for producers of any experience level. Radio makers from all over the world will have 24 HOURS to write, record, and edit a nonfiction radio story. On Saturday, August 2nd, at 10AM PT, contestants will be emailed a THEME. They will then have 24 hours to create a story that somehow relates to this theme. By Sunday August 3rd at 10AM PT, their finished piece must be posted on Soundcloud for judging.
With only 24 hours to complete a finished piece, the last thing anyone wants to do is transcribe from scratch. That’s why we’re offering exclusive access to our auto-transcription toolkit. Use Pop Up Archive to help craft your Radio Race stories, and receive one full month of uploads for free! Email us at firstname.lastname@example.org with the subject line “Pop Up Radio Race” to redeem your free month of access.
READ ON FOR OUR GUIDE TO THE POP UP ESSENTIALS:
5 unexpected insights from automatic speech recognition
Pop Up Archive has been hard at work implementing new speech recognition software for our partners at organizations like NPR, StoryCorps, and the Hoover Institution. The result of this work means better auto-transcripts, and better auto-transcripts mean better access into hours upon hours of spoken content locked in digital audio.
Along the way, we’ve learned some surprising things about the state of automatic speech recognition. Here’s our crash course in the workings of speech-to-text software:
1. Speech-to-text software learns language like people do.
All automatic speech recognition software learns from whatever data it’s given. So, like a person, the more “well-read” your software is in a particular area, the more it will understand.
2. The human standard for perfect transcription is being questioned.
The gold standard for transcripts has always been human transcription. But as machine learning gets better, a human transcriber won’t necessarily transcribe more accurately than a computer for unfamiliar dialects. Speech-to-text software is trained on many voices, so it can interpret dialects from all over the world. Check out this 2011 Google Tech Talk on “Superhuman speech recognition.”
3. Speaking clearly can make you harder to understand.
Since most speech software is trained on naturalistic pronunciations — that is, how you would say a word in a real conversation — speakers that over-articulate may not be properly understood. For example, to clearly pronounce the “t”s in “butter” would go against the Standard American English pronunciation, which is closer to a “d” sound.
4. Not all vocabularies are created equal.
When you create a language model, it’s not just the number of words in the model that contributes to accuracy - it’s how well their distribution matches those of the content.
5. We’ve only scratched the surface.
Speaker recognition. Accurate punctuation. Comprehensive geographical and biographical knowledge….
All of these features are not only possible in automatic speech recognition, but will soon be on their way into your own Pop Up Archive auto-transcripts. As we integrate the new software into Pop Up Archive over the next few months, you’ll see major improvements to our automatic transcription and editing tools. We’ll keep you posted as our new features become available!