YouTube Has Speech-to-Text Functionality…..and it Works

By on 07/31/2008 9:55 AM @beet_tv

YouTube has introduced rich metadata into select videos, which will significantly impact how online video is discovered and consumed.

Announced in June, we have found the technology is very useful.  Last week, we got an update on this from Steve Grove, head of news and politics at YouTube.

YouTube applies a technology in which automated spiders “listen” and
transcribe the words in the audio track of a video.  This transcription, in the form of
metadata, is embedded into the video.

This new speech-to-text technology has been applied to campaign videos from John McCain and Barack Obama
as well as non-campaign produced clips.  The search box is found on
YouTube You Choose page.  (It’s on the lower left area of the page.) Visitors can enter words such as “Iraq, “Global Warming,” and
“Free Trade.”  Also, putting your cursor over the timeline, you can see the transcription.

Youtubebox_3

While this is the first voice-to-text speech application at YouTube and will likely expand, this
is an emerging area in video search.  Companies including Blinkx,
EveryZing and Delve are providing voice-to-text transcriptions in the form of metadata.

Later this year, Adobe, will provide speech-to-text technology into the Flash video production environment, Beet.TV has learned.  This is a critically important development in bringing effective search to online video.

I interviewed Steve at Stanford last week where he was a panelist on the Beet.TV online video
roundtable.

Here’s story about YouTube and the new voice-to-text features by Anthony Ha at Venture Beat.

McCain’s Obama Celebrity Video is Blockbuster on YouTube

Uploaded to YouTube less than 24 hours ago, the McCain campaign ad about Obama’s “celebrity” status, comparing him with Britney Spears and Paris Hilton, has had 750,000 views at this  hour.

Andy Plesser, Executive Producer

Recent Videos
image
UGC-Based Broadcast is #1 New Syndicated Show in U.S.

LAS VEGAS – The manpower and resources behind local news have shrunk but the time frames have not, leading to a lot of repetition in news programs, says Phil Alvidrez, executive in charge of production for RightThisMinute, a TV show that publishes online video content – and tells the story behind it – ...

image
Dolby Readying “Cinema-Like” Audio for Mobile Video

LAS VEGAS – With the advancement in second-screen and mobile technology as companies like Apple and Amazon rolled out mobile devices that could support high-definition video, consumer expectation for high-quality sound on their tablets and phones increased, says JC Morizur, senior director of professional ...

image
Live Video Streaming Format MPEG Dash Embraced by Akamai, Google, Adobe, Microsoft others

LAS VEGAS – MPEG Dash — the emerging live video format for cross-platform streaming, has picked up considerable traction over the twelve months with the participation of major players including Google’s YouTube, Microsoft’s Azure, Adobe Primetime and Akamai, explains Will Law, Chief ...

image
Microsoft says Streaming Olympics was Turning Point for its New Cloud Offering

LAS VEGAS —  Microsoft’s global, cloud-based platform for delivering video, called Azure, is gaining momentum and customer wins in the aftermath of its successful streaming of the Winter Olympics, says Bob DeHaven, GM of Worldwide Communications and Media, in this interview with Beet.TV The ...

image
Microsoft Announces Support for Fast-Emerging Streaming Standard MPEG-Dash

LAS VEGAS  – One of the top stories from the NAB Show was the accelerated support of streaming  video standard MPEG-Dash, perhaps  most notably with the announcement from Microsoft that it will support Dash with its media solutions. At NAB, we interviewed Iraj Sodagar, Principal Multimedia Architect ...

image
Making Content Marketing Accountable To Drive Business, MediaCom’s Sean Black Explains

Content marketing has always been a part of advertising, but the big difference is that content is finally accountable, says Sean Black, Managing Partner and Group Digital Director at MediaCom, during an interview for Beet.TV with Paul Kontonis, SVP Strategy & Sales at Collective Digital Studio. ...

image
Branded Video Must be Tailored to the “Venue,” Mindshare’s Migliozzi

Branded video performs best when it’s tailored properly to the platform, says Joe Migliozzi, Digital Lead at Mindshare NA, in an interview for Beet.TV with Paul Kontonis, SVP Strategy & Sales at Collective Digital Studio. “The consumers are defining the platforms for the brand. If ...

image
Digital Planning will Come to TV Ad Buying, but Not So Fast, Nielsen’s Amit Seth

SAN FRANCISCO – While measurement tools like Nielsen’s OCR allows TV ad buyers to identify online audiences to match TV buys, which are primarily for “make goods,” there are strong headwinds against changing the way that TV ads are sold via upfronts and other conventional means, ...

image
Old Fashioned, “Mad Men” TV Ad Trading Must Stop: Mediaocean’s Woollard

SAN FRANCISCO — Programmatic ad trading techniques could eliminate costs and cut time by bringing ad buying in to the digital 21st century, says one ad tech vendor. “The way that TV is bought has been the same way since the Mad Men days – I pick up the phone, I do a deal,” says ...

image
Ad Buyers Want Linear TV Sales To Go Programatic, Experts

SAN FRANCISCO — IPG’s insight agency Magna Global is using the current TV upfronts, the annual process by which TV networks sell advertising inventory for the year ahead, to push cable networks to adopt programmatic trading techniques. Says Magna Global USA president Kristi Argyilan: ”We ...

image
‘Programmatic Is Not Just For Performance’: Magna Global’s Brunick

SAN FRANCISCO — Data-driven buying processes beget data-centric advertising. At least, that’s how the evolution of the collection of automated and algorithm-heavy trading techniques dubbed “programmatic” has played out so far. But are things changing? “We’ve put it in to a ...

image
Elemental Technologies Now Powering Video Encoding for BBC iPlayer, Integration with Adobe Primetime

LAS VEGAS – Elemental Technologies, the Portland, Oregon-based video encoding software company is powering the “the BBC iPlayer infrastructure,” says CEO Sam Blackman, in this interview with Beet.TV at the NAB Show. For the BBC and other customers, the video encoding happens increasingly in ...

loader