Blog

Exploring Smarter Video Transcription to Support Universal Design for Learning and Cost Savings

Exploring Smarter Video Transcription to Support Universal Design for Learning and Cost Savings

Higher education institutions share a goal of making learning more accessible to all students. To meet this goal many colleges and universities, including UMass Amherst, have adopted the Universal Design for Learning (UDL) framework in an effort to design curriculum to serve all learners, regardless of ability, disability, age, gender or background. Modern technologies often play a supporting role in UDL, providing students with multiple modalities such as video, audio, and text. While these technologies can make implementing UDL easier, they can also be costly.

Beginning with the Fall 2018 term, an interdisciplinary team of academic technologists, instructional designers, and instructors at UMass Amherst started exploring how classroom video and Echo360’s new automated speech recognition (ASR) technology can create a pathway to cost-effective, scalable captioning that can improve accessibility and support universal design.

UMass Amherst relies on Echo360 to deliver video for nearly 300 courses and to record over 100 special events and guest speakers throughout the year. Faculty at UMass Amherst use Echo360 to record and stream lectures live, to flip their classes by putting lecture content online, and to engage their students through classroom discussions, live or asynchronous polls, and “low-stakes” quizzes, and assist students with disabilities and give them the most equitable experience possible. To kick off the project to evaluate Echo360’s ASR solution, they started with 6 courses in the pilot program.

The Need for Affordable Video Captioning and Transcripts

The high cost of professional captioning is a significant barrier for institutions. According to Daniel Cannity, instructional design & faculty support coordinator at UMass Amherst, the cost to caption a single course can be as much as four thousand dollars.

“In an average academic year at UMass Amherst, we run 783 courses using Echo360,” says Cannity. “It is not economically feasible to transcribe and caption every course at a cost of several thousand dollars. We have made accommodations on a case-by-case basis, but if we have a goal to make content accessible to every student and support Universal Design for Learning, we must find a sustainable and economically feasible option. That’s where Echo360 comes in. It provides a cost-effective alternative, minimizing the workload for instructors and cost for institutions.”

Better, Faster Transcription Makes the Captioning Process More Affordable

The faculty at UMass Amherst is as diverse as the student body it supports. Instructors come from around the world and many are non-native English speakers, who speak with a variety of accents. Different accents and technical vocabulary create challenges for any speech recognition technology, which lead to less accurate transcripts.

“Echo360’s solution is based on the same technology that drives Amazon Alexa,” says Cannity. “Every algorithm set; every machine learning option out there has the same issues. But, given the popularity of Alexa and the number of users with different accents, it will only get better over time.”

Additionally, according to Cannity, the amount of time it takes to create a transcript using Echo360 is faster than traditional transcription services.

“The rule of thumb is one to three,” says Cannity. “With traditional transcription, for every minute of content you have, it takes about three minutes to transcribe it. But, even for faculty who have the least accurate transcripts, the time it takes to correct their transcripts and caption the video with Echo360 is much less. We’re able to create a transcript and captioned video and save about two-thirds the time that it takes for traditional transcription and captioning.”

Transcripts and Video Help Students to Focus and Study

Early student feedback during the pilot has revealed important ways in which ASR can support universal design. While transcripts and captions allow students with hearing disabilities access to video content, there are other measurable learning benefits that help learners beyond those who have disabilities. One such benefit is repetition by reading and listening.

“Students have reported that the transcripts and captioned video help them focus,” says Marisha Marks, instructional designer online education. “For others, English may not be their first language and they have said how much they appreciate having a transcript. None of these students would have been covered by traditional captioning services. It’s a great first step that offers an affordable transcription option for us. It definitely meets universal design criteria,” adds Marks.

Beyond reading and listening, the Echo360 transcripts are searchable. “The searchable transcript can become a student study aid,” says Marks. “The interactive transcript window lets students search for specific sections of content without having to watch or scan through an entire lecture. They can search for and easily locate the specific content they need.”

UMass Amherst will continue the pilot project during the Summer and Fall 2019 terms. This will help the University to continue to refine and improve workflows, add to the number of instructors using ASR for their courses, and elicit additional student feedback.

From automated speech recognition, secure video assignments, to flipped classrooms and more, learn why Echo360 is the smarter video platform for education. Contact us to learn more and schedule your personal demonstration.