ChaCha Beats Google and Yahoo in Mobile Voice Search Tests


Mobile analyst firmMSearchGroovehas just published the results of a series of tests which show that the mobile search serviceChaChabeat out two other voice-enabled search applications on the iPhone when it comes to search query accuracy.[Update, Ed:a commenter points out that the report was actually sponsored by ChaCha]To test this, the researchers usedGoogle's own mobile applicationandVlingo for iPhone, an app that lets you search both Google or Yahoo. Oddly, they ignoredYahoo's mobile app, which also has voice search built in.

The results of their study aren't entirely shocking: if you want to be understood, ask a human, not a computer.

The Mobile Search Tests

ChaCha's mobile search servicecan be accessed both by SMS and by calling a toll-free 1-800 number. Since these tests focused on voice search, the phone-in method was used. When using ChaCha, the service identified the queries accurately in 94.4% of the cases and delivered accurate search results 88.9% of the time. Vlingo, which the researchers used to test Yahoo search, only interpreted queries correctly in 72.2% of the cases and delivered accurate results 27.8% of the time. Google, surprisingly, fared worst of all. Their mobile application only understood spoken queries in 16.7% of tests and delivered accurate results 22.2% of the time.

To test the applications, the researchers conducted two rounds of tests using both keyword search and natural language queries where they asked questions using sentences. The queries represented a cross-section of typical mobile searches in categories like navigation, directions, local search, general information, social search, and long-tail search.

It's not all that surprising to find thatChaChaoutperformed the other voice-enabled applications - after all, they have real, live humans on the other end of the line to interpret the spoken questions. What is surprising, though, is how wide the gap is in between the human-powered search and the speech recognition apps,especiallywhen contrasting ChaCha with Google.



Sensory Announces 'Truly Hands-Free,' the First Always-On, Always-Listening Voice Control for Bluetooth Devices

Sensory Inc., has announced Truly Hands-Free, a significant enhancement to the BlueGenie Voice Interface, the leading voice control and speech output solution on Bluetooth headsets. For the first time, Bluetooth devices -- including headsets, car kits and stereo headphones -- will benefit from a hands-free trigger or phrase spotting technology. With Truly Hands-Free, the BlueGenie Voice Interface is always listening and virtually impervious to background noise so the user can initiate functions without using even one button trigger.

Mobile Speech Applications Market Set To Triple By 2014

Speech recognition software is expected to increase considerably in the next 5 years as today’s world becomes even more fast-paced.

As part of their latest report, independent data analyst Datamonitor has forecasted that the global market for advanced speech recognition (ASR) technology in mobile devices is set to triple to $99.6 million by 2014 from the current $32.7 million and that ASR in-vehicle telematics will also grow to $208.2 million from the current $64.3 million.

Mobile speech applications allow users to voice-control the operation of a device. Speech applications are also widely made use of in voice-based search for voice-dialing and voice input, where a user can vocally upload data. Also, the increasing trend towards restrictions placed on operating mobile devices while driving is expected to contribute to a growth in the speech recognition software market.

Globally, several nations, including 15 states in the U.S., have come forward to enact legislation that restricts the use of handsets while operating vehicles. Most of these legislations permit the use of hands free devices as an alternative and telecom carriers have been promoting command and control and SMS based services to combat theses restrictions.

In-Vehicle Telematics also make use of ASR and text-to-speech technologies, commonly to input addresses, manage music playlists, read out addresses and more. With an increasing number of devices using network based ASRs, recognition rates have also improved.  In addition to this, the popularity of application stores have allowed feasible options to emerge for smaller operators who can now reach out to the market and provide innovative solutions.

ARM Based TI Chip Drives Headset So You Can Forget A Laptop

The days of lugging a laptop around may be over, thanks to Kopin Corporation’s Golden-i - a lightweight Bluetooth headset providing a 15 inch virtual display with hands free speech recognition, which is driven by an OMAP3 dual processor platform from Texas Instruments.

The three ounce device uses natural speech recognition for wireless remote control over an array of host devices from cell phones and PCs to company networks and wireless systems. Golden-I accepts conventional user interface from any host device touch screen, keyboard or wireless mouse.
Golden-i provides hands-free spontaneous access to all digital information, broadcast programming and Internet services, including real-time, full-color D-1 high resolution (720 x 480p x 30 fps) streaming video over industry standard Bluetooth 2.0 which was developed in partnership with BlueRadios, Inc., the company said.

Running the 32-bit native, componentized, hard real-time Microsoft Windows Embedded CE 6.0 R2 operating system, Golden-i is capable of remotely waking a PC from practically any location. After Golden-i establishes a Bluetooth, WiFi or cellular link through a host device, users will see their PC desktop screen on a 15-inch virtual display, offering full hands-free access to all PC applications, data files and services. When work is finished, the PC can be placed in hibernation with a single spoken command. With Golden-i, users will no longer need to carry a PC or laptop everywhere they go.

Hands-Free Car Kits Not Truly Hands-Free

The Strategy Analytics Wireless Device Lab service research, “Hands-Free Car Kits: Consumers Lack a Truly Hands-Free Experience,” shows that purchasers of after market car kits in the UK would like to use speech recognition in order to make their car kit experience truly hands-free; but speech recognition systems fall short of expectations.


These findings are based on in-depth one-on-one research sessions with participants near London, England.

“Strategy Analytics research shows that consumers would like their car kits to provide easy and intuitive hands-free methods for dialing and answering their cell phones while driving,” commented Chris Schreiner, Senior User Experience Analyst at Strategy Analytics. “However, consumers struggle with speech recognition due to usability issues.”

Kevin Nolan, Vice President of the Strategy Analytics User Experience Practice, added, "Our research also shows that streaming music is a service in some car kits that adds value for the consumer, although consumers prefer to experience music via direct hookup through their vehicle speakers rather than via an FM transmitter.”

Speech Recognition Software Hits Blackberry

SHAPE Services GmbH today announced the availability of a speech recognition feature in IM+, the mobile instant messenger. SHAPE has joined forces with Yap Inc., pioneer of the first fully automated voice-to-text platform, to add the first of its kind, thumbs-free message dictation feature to IM+ for BlackBerry(R) smartphones.

IM+ with speech recognition will allow users to dictate their instant messages and send them as text to their contacts in Facebook(R), AIM(R)/iChat, MSN(R)/Windows Live(TM) Messenger, Yahoo!(R), ICQ(R), Jabber(R), Google Talk(TM) and MySpaceIM. Recent studies indicate that over 70% of consumers prefer using voice to interact with their mobile devices rather than typing. Speech-enablement increases message creation speed and greatly improves the usability of instant messaging on mobile devices.

Windows Mobile gets enhanced voice-command capability

Microsoft Corp. has high hopes that a new speech-recognition application for the forthcoming Windows Mobile operating system will be attractive enough to draw people to the phone platform.

Microsoft today planned to announce a new service that will work on Windows Mobile 6.5 devices and will let people speak into the phone to search the Internet, make phone calls and dictate text messages. Thetechnology comes from Tellme Networks Inc., a company that offers hosted voice recognition services and was acquired by Microsoft in 2007.

Tackling the Bit Pipe Nightmare with a post-ARPU strategy

The bit pipe nightmare has lurked in the industry’s sub-consciousness for many years now. The threat stemmed from how the Internet would merge with mobile communications, smashing down the traditional operator and subscriber relationships. So far this threat has been contained. Mobile operators adopted a walled garden approach where they aimed to hold on to an exclusive relationship with their customers and gauged their value by the money spent directly with them. And, despite the proliferation of viable mobile broadband, subscribers haven’t strayed very far from the walled garden. That is until now.

In July 2009 the Apple Apps Store will be a year old. Its effect on the operators’ relationships with their customers is profound. Already 500 million iPhone applications have been downloaded from the Apps Store. Other handset vendors like Nokia and RIM are re-modelling themselves as app and media service providers with varying success. As a result, these brands and businesses are developing a myriad of direct relationships with operators’ customers through these new app storefronts.

Given this scenario, which is shared with many households other than mine, it is natural that the mobile operators are now keen to offer similar storefront offerings to their customers. But is this enough? And how can they re-capture the initiative?

Lyrix and Loquendo Partner for Improved Speech Recognition

In a bid to further improve the functionality of their Mobiso service, Lyrix, a provider of speech-enabled collaboration solutions for large and distributed enterprises, has partnered with speech technologies provider Loquendo.   Lyrix’s speech-enhanced directories are used for Speech Attendants and Speech-assisted Mobile Address Books. The company’s PeopleFind platform also helps businesses with increasingly on the go workers to more efficiently communicate while also reducing costs.