Machine Learning | Clifford B. Andersonhttps://www.cliffordanderson.net/tags/machine-learning/Machine LearningHugoBlox Kit (https://hugoblox.com)en-usFri, 29 Jul 2022 00:00:00 +0000https://www.cliffordanderson.net/media/icon_hu_1f25fc939507c92a.pngMachine Learninghttps://www.cliffordanderson.net/tags/machine-learning/Automated Speech Recognition Aids in Transcription and Captioning for 62,000 Hours of Archived Television Newshttps://www.cliffordanderson.net/blog/television-news-transcription/Fri, 29 Jul 2022 00:00:00 +0000https://www.cliffordanderson.net/blog/television-news-transcription/<p>Jim Duran, director of the Vanderbilt Television News Archive (VTNA), announced the completion of transcription and captioning for 62,000 hours of recorded television news that began in 1968 and continues today. Captioning improves the archive&rsquo;s accessibility by supporting users with hearing impairments and opens the archive up to new methods of research using text and data mining.</p> <p>Working with Associate University Librarian Cliff Anderson, Duran designed a workflow using four Python scripts running simultaneously on three different machines to automate the transcription process, resulting in 89,000 transcriptions covering 62,000 hours of content. By applying a custom language model to the Amazon Web Services Transcribe service, Duran and Anderson increased transcription accuracy using examples of text that closely resembled the output of a television news transcript. </p>