Sign up for our daily recaps of the ever-changing search marketing landscape.
The SEO Impact Of Google’s New Speech Recognition In Videos
Google has rolled out Google Audio Indexing for video just in time for the final stretch of the U.S. presidential election. Using speech recognition technology, Google has indexed all the words spoken within YouTube political channel videos. This allows users to find videos that contain their search term and navigate directly to the part of the video where the term was used. Videos can also be filtered by candidate- Obama or McCain.
Here’s an example:
According to Google, the new audio indexing system, called GAudi, uses speech recognition technology to transform speech into text and then ranks videos by (1) spoken keyword relevance (2) YouTube metadata (3) freshness. Being in beta, Google’s speech recognition technology still isn’t perfect and occasionally gets tripped up on unclear speech or words that have different meanings. Then again, perfect transcription of speech to text is difficult to achieve.
For example, in this video, is Obama talking about what he just ate at the Indiana Jefferson Jackson Dinner?
SEO implications of speech to text in video
YouTube political channels are just the beginning. For the time being, candidates control the content in GAudi based on the videos they upload to their custom YouTube channels. After the election, look for Google to roll GAudi out to all YouTube channels. This gives all publishers the chance to get their speech content indexed, potentially increasing visibility in search.
GAudi could make YouTube an even more powerful tool for video SEO. We already know that the best chance publishers have in winning high rankings for their video content is to upload content to YouTube. Google and Yahoo! have an easier time reading YouTube video metadata than they do reading video housed on a native site. What if GAudi was rolled out to Google.com and YouTube videos started ranking for keywords spoken within them? Imagine speechwriters thinking about the keyword density for targeted search terms in the speeches they write.
Improved relevancy. Ever come across a YouTube video that has nothing to do with what’s written in its title or description tags? While GAudi still figures metadata into the rankings, it uses spoken keyword relevance as its most important ranking factor. More relevant YouTube search results on Google.com mean that Google.com will likely send even more traffic to YouTube. This is another reason that publishers may want to start their own YouTube channel.
If Google can solve the common problems of speech-to-text translation, GAudi, with the power of YouTube distribution, has the potential to open up a huge amount of spoken content to searchers. Depending on how this technology progresses, SEOs should keep GAudi in mind when thinking about optimizing and distributing video content.
Some opinions expressed in this article may be those of a guest author and not necessarily Search Engine Land. Staff authors are listed here.