Expert on language standardization and coding joins Philips to develop and expand service portfolio for healthcare speech recognition

Royal Philips Electronics (AEX: PHI, NYSE: PHG) announced today that it has appointed Dr. Theo Bosma to help expand its portfolio of professional services for information capturing in healthcare. Dr. Bosma, who joins from Aurora, Colo.-based Health Language, Inc., will hold the position of business development manager at Philips Speech Recognition Systems. With more than 20 years of experience in healthcare and technology-related fields, including business consulting and large IT project management, Dr. Bosma is an expert on standardized terminology and coding.[click heading for more]

Philips, Oy Konttorityö introduce speech recognition-based hospital report management solution in Finland

Royal Philips Electronics announced today the release of a report management solution for Finnish hospitals that is expected to significantly speed up the availability of medical reports and information. Philips SpeechMagic Executive Advanced (SMEA) caters to a variety of medical documentation use cases from dictation and transcription to speech recognition. The system seamlessly integrates with any healthcare infrastructure and features the new Finnish MultiMed ConText for hospital-wide speech recognition. The solution strengthens Philips position as the only company to provide healthcare speech recognition solutions for the major Nordic countries, including Finland, Norway, Denmark and Sweden. [click heading for more]

Google Demoes Video Search with Speech Recognition

Google released a demo for a speech-to-text technology that allows you to search inside a video's content. You can add an iGoogle gadget that is restricted to a small number of political videos from YouTube. Since the gadget is actually an iframe, you can also go to the original page. [click heading for more]

NewVoiceMedia Announces British Patent

Hosted contact center provider NewVoiceMedia has announced that it has been granted a UK patent for its Computer-Telephony Integration as a Service. From today, any call center can implement the handling by using an 08XX number and renting the NewVoiceMedia service as on-demand. "There's no new hardware or software integration required, and users can still use their existing switch," NewVoice officials say. [click heading for more]

Nuance's SmartListener Technology Boosts Speech Recognition Automation and Accuracy

SmartListener technology takes Nuance's real-world grammar design experiences from the Nuance Deployment Databank and applies it to the design of any existing speech solution. Armed with this information, an automated system can better focus on the concept behind the caller's words and decipher the caller's actual request. The resulting system adapts to a larger variety of more natural responses from callers. SmartListener technology accomplishes this feat by using Nuance's Adaptive Grammar Engine to transform the grammars from an existing speech solution into adaptive grammars. Within just a few days, businesses can deploy a more accurate, easier to use speech solution with low effort, low cost, and rapid time-to-market. [click heading for more]

Can biometrics make banking more secure?

VILLAINS, beware. The fight against online fraud has a new weapon—the panic finger. Banks in Europe and South Africa are testing a device that authenticates online transactions by asking customers to run their fingerprint over a reader. If the print matches a stored copy, the device, which is made by Siemens, a German firm, and AXSionics, a Swiss firm, shows a PIN code that can then confirm the transaction.
Consumers can enrol more than one finger when they start using the scanner. That adds yet another layer of security: worrywarts can set the device to require a concerto’s worth of fingerprints before it gives out the PIN code.
It also allows people to designate a panic finger, for use if fraudsters are forcing customers to use the device. Swipe the said digit across the scanner and the transaction will appear to go through as normal even as the bank is alerted that something fishy is going on. For the truly neurotic, there is yet more reassurance. Criminals who are tempted to hack off customers’ fingers will be disappointed: the scanner has to detect circulating blood to work.

But two big hurdles remain—convenience and cost. Training customers to use something new is never easy. Scanning fingerprints adds time as well as security. And the device is another thing to lose or break. Systems based on voice biometrics look more user-friendly: people already use telephones, and can do so on the move. Voice signatures can also make transactions swifter, by cutting out the need to enter account details.
The economics are an even bigger barrier. The costs of the technology are coming down, but the device is still more expensive than other systems. Creating passwords costs virtually nothing and smart-card readers for use at home are much cheaper too [click heading for more]

Why can’t I learn a new language?

[nik's note: not about speech technology per se, but an interesting insight into human language acquisition]

People comprehend their native language with great speed and accuracy, and without visible effort. Indeed, our ability to perform linguistic computations is remarkable, especially when compared with other cognitive domains in which our computational abilities may be rather modest. My work deals with one aspect of language processing, namely, the identification of sounds, which is needed for subsequent word recognition. Sound recognition is a complex task, because the same sounds may be spoken differently depending on the speaker’s sex, age, pitch of the voice or mood. In addition, people may whisper or shout, be in a quiet room or a noisy street. All of these, and many other factors, lead to huge variation in individual acoustic instances of the same sound. It is precisely this acoustic variation that for decades has caused problems for computational linguists and speech engineers building automatic speech recognition systems. Humans, however, even five-year-olds, can successfully recognise sounds and words and under-stand what other people say almost instantly.

So what allows humans to be so efficient at sound recognition and how does that impact on our ability to learn a new language? [click heading for more]

New Study Proves Safety Benefits from Speech Recognition Use in Automobiles

[Nik's Comment: no surprises here in the results, after all, who is it makes in car recognition systems? :) ]

Up to Twelve Times Less Swerving and Three Times Better Reaction Time Seen When Using Speech Recognition to Control Music, Navigation and Phone Devices in the Car. Nuance Communications today released the results of a 2008 In-Car Distraction Study, which measures the positive impact to safety and response times when people use speech recognition to control their in-car systems. The new study revealed significant benefits when drivers were able to use their voice to select music, input addresses in navigation systems and dial the phone while driving.

The most significant finding of the 2008 In-Car Distraction Study is that speech-recognition significantly reduces distractions and improves driving performance while selecting music, making calls and using navigation systems in the car. Further, the data shows that speech recognition, combined with Nuance's natural language understanding technology, delivers the most dramatic benefits in reducing distractions in the car. Natural language understanding enables speech interfaces to accept multiple variables in a single voice command, such as "Go to Broad Street, Philadelphia" versus responding to independent prompts for city, street and street number.

click heading for more]

Speech self-service speaks the language of savings

Speech self-service is still a minority toolset in the touch tone-dominated call center world, but its impact on the customer experience continues to improve for such companies as DirecTV and Orbitz.
Alan Hubbard, senior vice president of Aberdeen Group's customer service and support group, reveals that while only 20% of best-in-class companies have speech self-service, 86% of those firms have seen their customer retention and satisfaction rates climb. They have also witnessed a 10% drop in abandoned calls. [click heading for more]

Nuance Launches 9 Languages For Speech Recognition

Nuance Communications has announced the availability of nine new Indian languages for speech recognition in the contact centre. The new language packs are available for Nuance Recognizer v9. The new languages now available, in addition to Hindi and Indian English, are Marathi, Malayalam, Tamil, Kannada, Telegu, Bengali, Gujrati, Oriya, and Punjabi. [click heading for more]