Google plans to add Speech Recognition to Search

June 30, 2011

This article is from Gail Johnson:

Technology Review - Published by MIT

Wednesday, June 29, 2011

Can Google Get Web Users Talking?

Voice-driven search is a futuristic idea, and may take some getting used to.

Tom Simonite

Audio:  Audio | |

Credit: Google

The notion of asking a computer for information out loud is familiar to most of us only from science fiction. Google is trying to change that by adding speech recognition to its search engine, and releasing technology that would allow any browser, website, or app to use the feature.

But are you ready to give up your keyboards and talk to Google instead?

Over the last two weeks, speech input for Google has gradually been rolled out to every person using Google’s Chrome browser. A microphone icon appears at the right end of the iconic search box. If you have a microphone built-in or attached to your computer, clicking that icon creates a direct audio connection to Google’s servers, which will convert your spoken words into text.

It has been possible to speak Google search queries using a smart phone for almost three years; since last year, Android handsets have been able to take voice input in any situation where a keyboard would normally be used. “That was transformational, because people stopped worrying about when they could and couldn’t speak to the phone,” says Vincent Vanhoucke, who leads the voice search engineering team at Google. Over the last 12 months, the number of spoken inputs, search or otherwise, via Android devices has climbed six times, and every day, tens of thousands of hours of audio speech are fed into Google’s servers. “On Android, a large fraction of the use is people dictating e-mail and SMS,” says Vanhoucke.

Vanhoucke’s team now wants using voice on the Web to be as easy as it is on Android. “It’s a big bet,” he says. “Voice search for desktop is the flagship for this, [but] we want to take speech everywhere.”

Voice recognition is more technically challenging on a desktop or laptop computer, says Vanhoucke, because it requires noise suppression algorithms that are not needed for mobile speech recognition. These algorithms filter out sounds such as those of a computer’s fan or air conditioners. “The quality of the audio is paramount for phone manufacturers, and you hold it close to your mouth,” says Vanhoucke. “On a PC, the microphone is an afterthought, and you are further away. You don’t get the best quality.”

Google asked thousands of people to read phrases aloud to their computers to gather data on the conditions its speech recognition technology would have to handle. As people use the service for real, it is trained further, says Vanhoucke, which should increase its popularity. Data from users of mobile voice search shows that people are much more likely to use the feature again when it is accurate for them the first time.

A bigger challenge to getting users to embrace voice recognition on the desktop could be the existing tools for entering information, saysKeith Vertanen, a lecturer at Princeton University who researches voice-recognition technology. “On the desktop, you’re up against a very fast and efficient means of input in the keyboard,” he says. “On a phone, you don’t have that available, and you are often in hands- or eyes-free situations where voice input really helps.”

Vertanen says people are less tolerant of glitches when using speech recognition on a desktop computer because of the close proximity of a tried-and-true way of entering text. He says users might find voice recognition more compelling on on other Internet-connected devices in the home. “Nonconventional devices like a DVR, television, or game console don’t usually have good text input,” he points out. Google TV devices can already take voice input spoken into a connected Android phone.

Vanhoucke acknowledges that speech recognition fulfills a more immediate need on phones, but argues that users are ready for it on conventional computers, too. “People will use it in ways that surprise us,” he says. “At this point, it’s still an experiment.” Situations when people may have their hands full is one example, says Vanhoucke (although it should be noted that desktop voice search today still involves using the mouse to activate the feature).

Google isn’t performing this experiment alone. The company is pushing the Web standards body W3C to introduce a standard set of HTML markup that allows any website or app to call on voice recognition via the Web browser, and has already enabled a version of this markup in the Chrome browser. For now, Google is the only major company with a browser able to use the prototype feature, but Mozilla, Microsoft, and AT&T are all working with the W3C effort.

“It’s a collaborative effort that other browser makers are part of,” says Vanhoucke. “Any designer can add it to their Web page. It’s something anyone can use.” Extensions for the Chrome browser that make use of voice input (like this one) have already appeared, and can be used to enter text on any website.

However, those extensions reveal that although Google’s desktop speech recognition is accurate for search queries, it’s not much good for tasks like composing e-mail.

Enabling the system to learn the personal quirks of each person’s pronunciation, a feature already enabled on Android phones, could address that. Vertanen points out that the personalization learned through mobile search could easily be ported over to the desktop for people logged into their Google account. It could also make it possible for the technology to spring up elsewhere. “The advantage of Google’s networked approach is that a [speech] model in the cloud can adapt to your voice in all these different places and follow you around, whether that’s in your living room or in your car.”

http://www.technologyreview.com/web/37913/page1/


Ohr Pharmaceutical Announces Clinical Squalamine Eye Drop Program for Wet-AMD

June 27, 2011

Ohr Pharmaceutical Inc. OHRP -2.91%announced today that it is advancing its clinical Wet Age-related Macular Degeneration (“Wet-AMD”) program with a novel topical formulation. Using its proprietary technology, Ohr reformulated Squalamine for ophthalmic indications from an intravenous infusion (“IV”) to a topical eye drop. The topical formulation is designed for enhanced uptake to the back of the eye and decreased potential for side effects. The previous IV formulation had been awarded fast track status and a Special Protocol Assessment (“SPA”) by the U.S. Food and Drug Administration for a Phase III registration study in patients with Wet-AMD.

Lucentis requires monthly injections directly into the eye; Squalamine delivered topically can be conveniently self-administered by the patient on a daily basis

Lucentis has the propensity for side effects and potential inherent complications of an intravitreal injection; Squalamine has shown a good safety profile even when administered systemically in significantly higher doses

http://www.marketwatch.com/story/ohr-pharmaceutical-announces-clinical-squalamine-eye-drop-program-for-wet-amd-2011-06-21?reflink=MW_news_stmp

 


Drug company treatments for macular degneration turn into a civil war

June 27, 2011

Say you have a serious disease and there are two drugs that can treat it. Both of the drugs are made by the same company, and they work equally well, but one costs $2,000 a treatment and the other $60. Which would you choose?

The answer seems obvious, but there are complications when it comes to the costlier Lucentis and the cheaper Avastin, the two drugs manufactured by San Francisco-based Genentech that are being used to treat wet macular degeneration.

Company executives did not respond to requests for an interview about the medicines. Instead, Terence Hurley, who asked to be identified as a Genentech spokesperson, sent an email that included this statement:

“The price of Lucentis allows us to continue discovering medicines for people with serious eye diseases. Genentech invested nearly a decade and hundreds of millions of dollars in the clinical development of Lucentis in wet AMD. It is one of the most expensive clinical trial programs Genentech has ever conducted.

“We will continue to invest in the science to allow us to continue discovering medicines for people with serious eye diseases.”

As for Avastin, Hurley said, “Genentech does not support or promote the use of Avastin for wet AMD or other eye conditions as it is off-label.”

The way Long Beach ophthalmologist Dr. Stanley Carson tells it, “Lucentis went though all the FDA trials to get approved for use in the eye. So the whole difference is because the company paid a


Advertisement

lot of money to run through the trials and experiments to satisfy the FDA. But they didn’t do it for Avastin.”

Carson means that although Genentech went through the same process to get Avastin approved for treating cancer, it never got the drug approved for treating macular degeneration.

How does Genentech feel about the civil war raging inside its family between two brother drugs? It isn’t saying, and to date, it still hasn’t done any research comparing the results of Lucentis and Avastin.

So the National Eye Institute commissioned its own research from February 2008 through December 2009, involving 1,208 patients age 50 and older at 44 clinical centers across the country. The results were published in the April edition of the New England Journal of Medicine. The bottom line was that both drugs were basically equally effective.

Genentech has not responded to the publication, but Hurley said, “We continue to believe that Lucentis is the most appropriate treatment for wet AMD.

http://www.dailybreeze.com/ci_18332265

 


Making a car for blind drivers

June 20, 2011

Using robotics, laser rangefinders, GPS and smart feedback tools, Dennis Hong of the Virginia Tech Robotics Lab  is building a car for drivers who are blind. It’s not a “self-driving” car, he’s careful to note, but a car in which a non-sighted driver can determine speed, proximity and route — and drive independently.

Here is his presentation at TED Talks.

http://www.ted.com/talks/dennis_hong_making_a_car_for_blind_drivers.html


Stem Cell Trials To Begin For Stargardt’s Treatment

June 20, 2011

Advanced Cell Technology Inc. (ACT) announced Thursday the enrollment of the patients in the trials for Stargardt’s Macular Dystrophy (SMD) and Dry Age-Related Macular Degeneration (Dry AMD). The patients were enrolled at the Jules Stein Eye Institute at the University of California, Los Angeles.

ACT won approval by the US Food and Drug Administration in January to use human embryonic stem cells for treating macular degeneration, a common cause of vision loss. That followed FDA approval in November for scientists to test the stem cells to treat people with Stargardt’s Macular Dystrophy. The new trials will test the safety and tolerability of retinal pigment epithelial, or RPE cells, which ACT makes from the human embryonic stem cells.

Animal studies have reportedly shown that injecting fresh RPE cells into the eye could bring about a substantial improvement in eyesight. In other studies, scientists said mice with eye disease recovered near-normal vision after receiving the therapy.

In addition to the Jules Stein Eye Institute at UCLA, the Casey Eye Institute (CEI) at Oregon Health & Science University (OHSU) in Portland, OR, is also open for enrollment of patients with SMD.

As additional sites are ready to enroll patients with SMD and dry AMD, they will be listed on the Clinical Trials page on ACT’s Web site and at http://www.clinicaltrials.gov.

http://www.redorbit.com/news/health/2066060/stem_cell_trials_to_begin_for_blindness_treatment/


Yahoo! Mail: Navigating the inbox with a screen reader

June 13, 2011

In a YouTube video, Todd Kloots, of the Yahoo! Accessibility Lab, shows how to navigate the new Yahoo! Mail inbox with keyboard shortcuts. This demonstration uses the NVDA screen reader and Firefox 4.

http://www.youtube.com/watch?v=_W0vjERCx4I

And a written supplement.

http://www.evengrounds.com/blog/accessible-experts-victor-tsaran


Retinitis Pigmentosa Reference Page

June 13, 2011

The first sign of retinitis pigmentosa is usually a loss of night vision, which becomes apparent in childhood. Problems with night vision can make it difficult to navigate in low light. Later, the disease causes blind spots to develop in the side (peripheral) vision. Over time, these blind spots merge to produce tunnel vision. The disease progresses over years or decades to affect central vision, which is needed for detailed tasks such as reading, driving, and recognizing faces. In adulthood, many people with retinitis pigmentosa become legally blind.

The Genetics Home Reference Page of the US Natl Library of Medicine has extensive info about Retinitis Pigmentosa, including possible treatment.

http://ghr.nlm.nih.gov/condition/retinitis-pigmentosa