![]() (I’m assuming that the podcasts will have clear high-quality audio.) At this point I’ve no idea how big that gap will be, though I’m confident it can be made small enough for this whole endeavour to be worthwhile. In other words, crowdsourcing of error checking and correction may be a viable way to close the “quality gap” between manual and automated transcriptions. A low-friction user experience makes that more likely. For a popular podcast there are likely to be some members of the audience (perhaps many) who are willing to contribute some amount of time to checking and correcting errors, somewhat like Wikipedia. Of course, an automated transcription is likely to have errors. Identify and show who is speaking, e.g.This requires the transcription to have timecode data. Provide buttons to play the audio/video from that point.Provide anchors to make it easy for people to link to a particular section, or sections, in the transcript.Produce podcast transcripts as plain text on static web pages that are indexed by search engines.Here is an outline of functionality that I’d like from a basic automated system: If not then I’m interested in starting a new project – or projects – and would welcome any help. I’m hoping someone will tell me that such a system, or parts of it, already exist so that I can contribute to those existing projects. I’ve also been updating it as I’ve come across extra information and new services. I sketch out some goals, constraints, and a rough outline of what I’m thinking of, along with links to many tools, projects, and references to information that might help. This (long) post is a record of my research and ponderings around this topic. This led on to some thinking about interesting user interfaces. Given the advances in automated speech recognition in recent years, I began to wonder if some kind of automated transcription system would be practical. It’s impractical to listen to hundreds of old episodes, so the content is effectively lost. When I remember fragments of some story or idea that I recall hearing on a podcast, I’d like to be able to find it again. A back catalogue of a year of podcasts would cost over $3,100 to transcribe. For a podcast producing an hour of content a week, that would add an overhead of around $250 a month. The typical solution is to pay a commercial transcription service, which charge roughly $1/minute and claim around 98% accuracy. ![]() Few of those podcasts have transcripts available, so the content isn’t discoverable, searchable, linkable, reusable. Americans, for example, now listen to over 21 million hours of podcasts per day. The medium of podcasting continues to grow in popularity.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |