Making sound searchable for the Digital Public Library of America

Case study: DPLA + Pop Up partnership

popuparchive-avatar-1000      dpla_square-logo_black

Since our founding, Pop Up Archive has made almost five million minutes of sound searchable. Much of that audio is housed by libraries, universities, and historical societies that comprise the nearly 2,000 member institutions of the Digital Public Library of America.

Pop Up Archive and the DPLA partnered in 2015 to offer exclusive discounted services to DPLA partner organizations. Here are some of the ways Pop Up Archive automatically transcribes, timestamps, and provides team editing interfaces for the audio collections of DPLA partners:

Wake Forest University

zsrlibrary-500x500Wake Forest University uses Pop Up Archive to transcribe oral histories that relate to WFU’s Center for Global Programs and Studies. Study abroad is a particular focus of the WFU student experience; about three-quarters of the student body spends a semester in another country.

Archivists at WFU’s Z. Smith Reynolds Library Special Collections & Archives capture first-hand accounts from American and international students, professors, program heads, and administrators about their experiences in other countries, in Winston Salem, and their view of the global Wake Forest’s future.

Collections archivist Stephanie Bennett says: “By using Pop Up Archive, we are able to generate transcripts that our student assistants edit. These will provide improved accessibility to these illuminating — and fun! — interviews once they go online.”

San Francisco Public Library

The San Francisco Public Library is in the midst of its first user experience service design project. The project is being undertaken by the Magazines and Newspapers Center in order to improve services and patron access to the SFPL’s rich collection of materials. One of the methods involves conducting interviews to explore patron expectations, pain points, and aspirations when they visit the library. The interviews are 30-45 minutes long, and “it’s a challenge to take detailed notes, so recording the interviews is a must,” says Andrea Davis, a librarian at SPFL. “We’re not going to listen and transcribe over 10 hours of tape by ourselves — we don’t have time.”

SFPL uses Pop Up Archive to search through transcripts of their user interviews — for example, searching for the term “parking” to find the point in an interview where a library patron discussed looking for parking near the library. They also use Pop Up Archive as an online tool so staff working on the project can share access to the interviews. “We go through and pull out the nuggets, and are planning a team listening party where we can all hear the library patrons in their own words, to build empathy and get the flavor of someone’s emotions,” Andrea says.

“Pop Up Archive has been a fantastic tool and we’ve utilized it for more than our original intent,” Andrea says. In SFPL’s next stage, they plan to map physical user journeys within the library, using the voice memo app on their cell phones to record interactions as they happen. They plan to experiment with Pop Up Archive to edit transcripts of the audio “trail” in order to add research and observation notes. “This whole project is new for the library — to do service design and research this way,” Andrea says.

Duke Divinity School

Students protest apartheid outside the Duke Chapel, May 4, 1985.
Students protest apartheid outside the Duke Chapel, May 4, 1985.

In 2014, Duke Digital Collections Program Manager Molly Bragg and University Archivist Valerie Gillespie set about digitizing the Duke Chapel recordings in response to divinity students’ requests to access the collection’s sermons, which date from 1946 to 2002. Since then, their team has digitized and made available 1400 audio/video items and 1300 printed manuscripts.

Duke uses Pop Up Archive to transcribe sermons with the goal of tagging and making them searchable by speaker, themes, and Biblical references. The university also uses the transcripts to create closed captioning files for hearing-disabled people. After revising transcripts with Pop Up Archive’s editor, student workers export the time-stamped transcripts as WebVTT files, which display as captions on Duke’s web video player.

The Duke Chapel Recordings web archive allows students to analyze sermons for theological and rhetorical components. It also serves as a historical resource, documenting Duke campus life and world events surrounding the sermons. “An archive of sermons offers [students] a relational time-machine, a gateway to the past where a preacher’s words reach out in a handshake, introducing their time, and place,” says Adrienne Koch, Project Director at Duke Divinity School.

Pop Up shares source code for public media speech-to-text software

Sharing software to make sound searchable



Cultural heritage institutions around the world house millions of hours of audiovisual content — but much of that sonic history is effectively unsearchable. Even when reels, tapes, and discs are digitized, the content they contain is opaque. Each digital file is like a black box, impossible to see within.

This week, we’re thrilled to announce a major open-source software release intended to help combat this problem. Over the course of this year, Pop Up Archive has trained special models, targeted specifically at public media content, for use with the widely-used open-source Kaldi speech-to-text software.

The development of this software is part of our work with WGBH and the American Archive of Public Broadcasting. Our goal is to make the American Archive — which contains over 40,000 hours of the most significant public radio and television programs from the past 60 years — searchable and discoverable.


To train our speech-to-text models, we collected millions of words from pre-existing public media transcripts and other content, then compiled the text into a language model, which is the component of speech-to-text software that deals with the probabilities of sequences of words or phrases.

If you’re curious for more details, take a peek at these slides prepared by Pop Up Archive computational linguist Tali Singer. You’ll also find our source code on Github.

This work was funded by an Institute of Museum and Library Services Research Grant for the “Improving Access to Time Based Media through Crowdsourcing and Machine Learning” project (see the full IMLS grant proposal or visit the American Archive site).

We’re very excited to make this contribution to to digital archiving and audiovisual communities. We’d love to hear from anyone interested in implementing the software at their own institution.

Case study: helping Snap Judgment tell stories with a beat

How Pop Up helps power the popular WNYC show


Snap Judgment is leading the pack of what Ira Glass has termed the “new wave of public radio.” With its one-two punch of stranger-than-fiction tales and cinematic sound design, the WNYC show doesn’t lend to casual listening; Snap’s audio mojo immediately hooks listeners, drawing them into an immersive world of real-life characters and extraordinary experiences.

Joe Rosenberg is one of the many talented producers digging up and dishing out stories for Snap Judgment. “The Writing Is On the Wall,” one of the pieces Joe is most proud of, tells about the murder trial of Alvin Ridley, a reclusive boogeyman to his small hometown of Ringgold, Georgia. Accused of imprisoning his wife for decades before murdering her, Ridley’s case seems open and shut until McCracken Poston, a local lawyer and failed politician, takes an unlikely interest in him and discovers there’s more to the misunderstood man.The retooled player is formatted to provide optimal readability and speed up your editing workflow. Instead of a line-by-line format, the new player displays text in paragraphs, much like you’d expect from any word processing software.


Joe conducted hours and hours of interviews with Poston, jurors, and other Ringgold locals to get the full story in the words of those who lived it. To manage all the tape he logged, Joe turned to Pop Up Archive. “Under deadline, I have to be extremely time efficient. Using Pop Up Archive is a major time management strategy for me,” he says.

Pop Up Archive transcripts not only save time that would otherwise be spent transcribing by ear, but they also give structure to Joe and his colleagues’ production process. “The transcriptions help me listen to the audio differently. I use them to select cuts from the raw tape and think about how I’m going to organize the piece,” Joe says.

We’re proud to help Snap Judgment save time and stay on point to deliver its trademark “storytelling with a beat” week after week.

Hear more of Joe Rosenberg’s work:
Headless Chicken
Speech Writer

Subscribe to Snap Judgment

Major improvements to Pop Up Archive

Better workflow, better prices: big news from Pop Up Archive


It’s time to let the cat out of the bag. We’ve been working behind the scenes for months to make Pop Up Archive even easier and more affordable to use, and we’re excited to chat you up about our new changes.

The spiffed up new look of your transcripts may have given us away. We just launched an updated version of our audio/transcript player that improves playback and text-editing functionality.

The retooled player is formatted to provide optimal readability and speed up your editing workflow. Instead of a line-by-line format, the new player displays text in paragraphs, much like you’d expect from any word processing software.


We also made the transcript more interactive: audio auto-plays for whatever text you’re editing, instead of requiring you to click a play button. Keyboard commands enable you to pause or rewind without having to click at all. Finally, we streamlined the process for adding and assigning speakers.

We could go on about the new player, but you should experience its many splendors for yourself. Give it a spin and see how easy it is to review and edit transcripts.


If you’re on a paid plan, your invoice may have tipped you off as well: new rates went into effect this month. As Pop Up Archive grows and speech-to-text technology becomes more cost-effective, we’re passing our savings on to you. Take advantage of our lower rates and upgrade to transcribe more audio:

1 Hour monthly: $20 => $15
5 Hours monthly: $75 => $65
10 Hours monthly: $150 => $120
20 Hours monthly: $300 => $240
25 Hours monthly: $375 => $300

As always, we welcome your feedback, questions, and suggestions.
Happy transcribing!
The Pop Up Archive team