The Stoop is a forthcoming podcast from Hana Baba, Leila Day, and Julie Caine that tackles oft-ignored aspects of race and identity. They describe the project as “a space where fun, funk, and journalism come together in a podcast that’ll go deep into topics about black identity that aren’t openly discussed.”
Presidential primaries are a huge deal everywhere, but they garner particular importance in states like New Hampshire, where their early timing positions them as bellwethers of what is to come. 2016 was one of the most contentious and protracted elections cycles yet, and New Hampshire Public Radio wanted to produce as much excellent primary coverage as they could — and make sure their primary night coverage was picked up by other stations across the country that were also following the race closely. Continue reading
Weatherbeaten wharves in New Orleans. Source: Wikimedia Commons.
To celebrate the tricentennial of New Orleans, WWNO — the NPR member station for New Orleans and the 13 parishes of southeast Louisiana — wanted to create something intimate and rich that captured the history of the city in a meaningful way. The result is “TriPod: New Orleans at 300,” a unique on-air program (and podcast) that, over the course of three years, celebrates the city’s past through short, documentary-style episodes.
Laine Kaplan-Levenson is the host and producer of TriPod. TriPod’s 10-minute episodes air bi-weekly, and each one is its own mini history documentary. A recent two-part episode (I, II) for example, told the story of a World War II internment camp called Camp Algiers that housed Europeans who the United States thought might be Nazis.
Laine produces the show on her own, but she has an auxiliary team of historians, professors, and museum curators who help her identify the stories behind some of the city’s most compelling pieces of history. Each month they sit down to discuss different topics to cover. After selecting the topic for the next show, Laine reaches out to people to start interviewing. As the sole producer, she knew she would need to rely on tools in order to keep up with the bi-weekly schedule, so rather than transcribe tape by hand — as she has done in the past — she signed up for Pop Up Archive. Continue reading
Teen angst. Embarrassing moments. Cringe-worthy choices. These experiences are the bread and butter of Mortified, the stage show and podcast that encourages ordinary people to “share the shame” of their childhood writing.
Dave Nadelberg founded Mortified in 2002, and today runs it alongside his producing partner, Neil Katcher. Together they help produce stage shows in 20 cities across the United States and the world — and transform a curated selection of those stories into three monthly podcasts. They use Pop Up Archive to automatically transcribe and tag tape in the editing process. Continue reading
“Pop Up has been a way to make our process more efficient and allow ourselves to put more online, which is more sustainable for our staff and better for Vermont Public Radio as an organization.” —Angela Evancie, VPR Digital Editor for News
Angela Evancie is the digital editor for news at Vermont Public Radio. She facilitates online stories for VPR’s website, repurposing broadcast news for the web and overseeing special web-only projects such as data visualizations, interactive features, and videos (like this nifty explainer about the Iowa Caucus from 2016).
Most of any public radio station’s content is conceived of as an on-air (audio) product; the digital editor’s job is to make sure that the station is also serving online audiences, who are reading or interacting with the story in ways other than listening. Angela and her colleagues at VPR use a Pop Up Archive team account to transform on-air pieces into written content for the VPR website.
Source: Vermont Public Radio
VPR has three daily news magazines — Morning Edition, All Things Considered, and Vermont Edition — and short interviews from each of these shows often find a second life as online articles.
A typical process starts with the radio broadcast being uploaded to Pop Up Archive. Sometimes, VPR editors take advantage of the fact that they’re publishing online as an opportunity to post a longer version of the original piece. “After we get the transcript from Pop Up Archive, then it then gets edited. If we’re keeping the online piece in an interview format, we’ll just edit it for accuracy. Other times, we’ll rework the transcript into an article format,” Angela says. Next, the article is posted to VPR’s content management system, given art and final polish, and published to the web. A few recent examples that went through Angela’s team to be republished as content for online readers include a story on a children’s book about coping with death, an interview with author Chris Bohjalian, and an interview with Vermont’s new attorney general.
VPR also leveraged Pop Up Archive in the weeks leading up to the general election. The station conducted interviews with all of the major and third party candidates running for statewide office: 24 interviews in total. The interviews occurred over several weeks and aired in different shows and segments. In order for the web content to be valuable to readers and voters, VPR wanted to package the interviews in such a way that their audience could do side-by-side comparisons of the candidates on specific issues. They used Pop Up Archive to transcribe the interviews and repackaged the interview highlights into a comprehensive voters’ guide. “The content was among our most successful in 2016, and it wouldn’t have been possible without Pop Up,” Angela said.
The process of transforming broadcast content into web content is one that occurs at VPR almost daily. But when Angela started at VPR three years ago, its web operations team was much less robust, and the process of translating on-air content into web content happened much less frequently. Each time they wanted to share a written version of a piece online, Angela or another producer would have to do their own transcription by hand.
Pop Up Archive has been an important tool for the station as its appetite to do more online, while being realistic about resource and time constraints, has grown. “Pop Up has been a way to make our process more efficient and allow ourselves to put more online, which is more sustainable for our staff and better for Vermont Public Radio as an organization,” Angela says.
See you in the archive,
The Pop Up Archive team
An emerging archival speech technology project is underway at the University of Texas at Austin, and its inspiration comes from a piece of software called ARLO that was developed to analyze an entirely different form of aural communication: bird song.
Called HiPSTAS (High Performance Sound Technologies for Access and Scholarship), the project is a collection of software tools and communication channels to help researchers access and analyze archival spoken word collections — for example, by analyzing audio spectrograms to identify particular traits such as pitch, tone, and speed. HiPSTAS was founded by Tanya Clement, an associate professor at the UT-Austin School of Information, along with collaborators at the University of Illinois Urbana-Champaign. The group has received several grants since its founding in 2012, including two from the National Endowment for the Humanities.
The ability to search archival spoken word recordings along multiple parameters has powerful implications for historical research and literary scholarship. While digital sound recordings are increasingly available to scholars, searching through the files for discernible patterns is time-intensive and cost-prohibitive.
Stephen McLaughlin is a research assistant and PhD student in Information Studies at UT-Austin and a contributor to HiPSTAS. Steve is currently working with WGBH and Pop Up Archive on the American Archive of Public Broadcasting, part of which entails a massive effort to use machine learning to identify notable speakers’ voices (for example, Martin Luther King, Jr.) from within AAPB’s 70,000 digitized audio and video recordings. As part of the AAPB project, Pop Up Archive transcribed the entirety of the AAPB and released free models for the open source speech-to-text software Kaldi, with the intention that the models could be used to enable other audio collections to be transcribed and thus searchable.
“The language models Pop Up Archive has assembled are more accurate, and do a way better job of identifying proper nouns, than other tools I’ve seen.”
While testing potentially useful tools to combine with HiPSTAS, Steve downloaded Pop Up Archive’s free models. “The language models Pop Up Archive has assembled are more accurate, and do a way better job of identifying proper nouns, than other tools I’ve seen,” said Steve. “The other exciting thing is that those models can be extended. I can take the model, transcribe a recording or correct its machine transcription, and use that output to make it more accurate for my needs. The flexibility of this system is really exciting.”
Kaldi is free software, released under an MIT License, that can be run on institutional servers, making it a natural choice for libraries, archives, and institutions that have a long-term approach and technical resources to support their projects. This is something Steve has personal experience with: “I’ve seen this happen, where commercial API services are here and gone. So the ability to run Kaldi locally is really an important tool to have in your tool belt. Pop Up Archive is providing a really valuable service by contributing their resources to a project like the Kaldi models.”
As an exercise, Steve recently used Kaldi to run through 80 hours of recordings by the poet Robert Creeley from the PennSound archive, the topic of his undergraduate thesis. Creeley used certain phrases and expressions over and over, such as the word “company” — so Steve searched the Kaldi transcript for every instance of “company” and then generated a supercut, combining the different tones and intonations into a continuous string of audio.
HiPSTAS team members are very interested to share what they’ve learned from their collective experience, and in the coming months Steve plans to publish code demonstrations for other researchers working with archival audio. He’d also like to write about his work with the American Archive of Public Broadcasting to identify speakers in large audio collections. Finally, he intends to run a workshop covering his work with Kaldi at one or more conferences later this year.
See you in the archive,
The Pop Up Archive team
Ear Hustle tells stories from life on the inside
“Before using Pop Up, we literally listened to tape and hand wrote it out. Or the other option was to listen to half a sentence, stop the tape, type it out, stop it, listen to more. It was insane; it took so much time. You could say that it made me hear the tape a lot more, but it was horrible and it was holding us back.”
—Nigel Poor, co-creator, co-producer, and co-host of Ear Hustle
Ear Hustle is a forthcoming podcast from Radiotopia, and the winner of Radiotopia’s Podquest competition to uncover innovative, rich stories and storytellers. Ear Hustle will tell stories of life within the prison system, revealing the experiences, characters, and perspectives of incarcerated Americans. And it’s told by the people living it. Continue reading
Peabody Essex Museum case study
“It could take half a day to transcribe an interview manually. Using Pop Up Archive, all we need to do is generate a working transcript and do a quick pass for minor edits and corrections.”
—Chip Van Dyke, Media Production Manager at Peabody Essex Museum
Trying to understand art can sometimes feel boring or confusing — but Chip Van Dyke, Media Production Manager at the Peabody Essex Museum (PEM) in Salem, MA, knows it doesn’t have to be that way.
The Peabody Essex Museum is one of the oldest continuously operating museums in the United States, and making art accessible is baked into their mission of celebrating “outstanding artistic and cultural creativity by collecting, stewarding, and interpreting objects of art and culture in ways that increase knowledge, enrich the spirit, engage the mind and stimulate the senses.” The content that Chip produces, largely in the form of videos of artists talking about their work, provides interpretation by situating the art in the context of the creator’s experience, perspective, and ideas. Continue reading
Case study: DPLA + Pop Up partnership
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
Wake 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
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.
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.