www.getdesign.in - My periodic blog exploring the world of business, experience design and interaction, with a smattering of gadgetry and social media. A world where business, people and technology meet.
Let's Fix Things: For over two decades I've been consulting in Communications Design: Everything from business strategy and processes, through to technology, interaction and customer experience. The thoughts here are my own, not necessarily that of my employer.
I have a penchant for spotting patterns and fixing broken user and customer experiences. Even my Bumblebee project hasn't escaped - I've been using Six Sigma techniques to study and predict their behaviour patterns. ☺
Starting today, Voxeo will offer Nu Echo's NuGram grammar development tool in an integrated package with Voxeo's VoiceObjects Service Creation Environment. This integration allows developers to easily create either static or dynamic grammars that can be used with VoiceObjects technology to efficiently build multichannel self-service applications.
Most people know that IVR applications should be extensively tested before they’re deployed. They should be tested to make sure that they perform as specified and that they will continue to do so under load. Yet, most applications are not tested nearly as much as they should, sometimes with dire consequences when a major problem is detected after the application goes live. One reason for this, naturally, is cost. Another reason is time, as slips in the project schedule often mean less time available for testing.
That’s where automated testing comes in. Automated tests should be a critical element of any IVR testing strategy since they can greatly reduce the time required for application testing, lower development costs, accelerate software release cycles, and increase application quality and stability.
Unfortunately, commercially available testing offerings are usually costly, complex to set up and operate, or both, which is why they are so rarely used. To address this problem, we have developed the NuBot Automated IVR Application Testing Platform, which we demonstrated this week atSpeechTEK 2009in New York City. The NuBot Platform is an affordable automated IVR application testing solution that is both powerful and easy to use.
[Nik's comment: it has to be said, appointing 5 suppliers as the outcome of a tendering process seems rather like skipping the tendering process! We await annoucements from the other 3!]
SRC appointed as a supplier under a four year framework agreement with the NHS Yorkshire and Humber Collaborative Procurement Hub (YHCPC). This agreement covers the deployment of SRC's digital dictation, voice recognition and outsourced transcription solutions to over 200 Acute, Mental and Primary Care Trusts.
Researchers at the Leipzig Max Planck Institute for Human Cognitive and Brain Sciences and the Wellcome Trust Centre for Neuroimaging in London have now developed a mathematical model which could significantly improve the automatic recognition and processing of spoken language. In the future, this kind of algorithms which imitate brain mechanisms could help machines to perceive the world around them.
Many people will have personal experience of how difficult it is for computers to deal with spoken language. For example, people who "communicate" with automated telephone systems now commonly used by many organisations need a great deal of patience. If you speak just a little too quickly or slowly, if your pronunciation isn't clear, or if there is background noise, the system often fails to work properly. The reason for this is that until now the computer programs that have been used rely on processes that are particularly sensitive to perturbations. When computers process language, they primarily attempt to recognise characteristic features in the frequencies of the voice in order to recognise words.
"It is likely that the brain uses a different process", says Stefan Kiebel from the Leipzig Max Planck Institute for Human Cognitive and Brain Sciences. The researcher presumes that the analysis of temporal sequences plays an important role in this. "Many perceptual stimuli in our environment could be described as temporal sequences." Music and spoken language, for example, are comprised of sequences of different length which are hierarchically ordered.
According to the scientist's hypothesis, the brain classifies the various signals from the smallest, fast-changing components (e.g., single sound units like "e" or "u") up to big, slow-changing elements (e.g., the topic). The significance of the information at various temporal levels is probably much greater than previously thought for the processing of perceptual stimuli. "The brain permanently searches for temporal structure in the environment in order to deduce what will happen next", the scientist explains. In this way, the brain can, for example, often predict the next sound units based on the slow-changing information. Thus, if the topic of conversation is the hot summer, "su?" will more likely be the beginning of the word "sun" than the word "supper".
BigHand has announced that following a tender and evaluation process, the NHS Yorkshire and Humber Commercial Procurement Collaborative has selected BigHand along with 5 other providers for the provision of digital dictation workflow software and speech recognition technology.
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.
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.
British speech recognition technology firm Eckoh is locked in a battle for boardroom control from its largest shareholder.
FT.com reports that 12 percent shareholder OCS Management has criticised executives’ performance and called for a new chairman to be appointed, while Eckoh execs are reportedly urging shareholders to resist its bid for more control and to back their own preferred candidate for the chairman position. Founder and CEO Nik Philpott ominously says he won’t “preside over the company’s death”.
Current chairman Peter Reynolds, who is stepping down at the end of the year, is expected to write to shareholders to drum up support—so far shareholders have been split in their allegiance. According to Reynolds, in initial meetings “OCS…stated that they saw little value in Eckoh’s Speech business but did see uses for the cash held by the company.”
James Golightly, executive director of OCS’ parent company ORA Capital Partners, says the plans is simply to “put a stronger board in place”. Expect fireworks at the company’s shareholder meeting on September 4.
Eckoh, the hosted speech recognition services business, has won a new five year contract worth a minimum £1.5 million to supply services to a major Government Transport & Infrastructure organisation.As part of the deal, Eckoh will provide automated telephone services using its advanced speech recognition technology, with the first service expected to launch later this year.
Promptu Systems Corporation today announced that the Italian version of its fully automated voice-to-text messaging application created for Telecom Italia Mobile (TIM) is now available to Italian iPhone owners from Apple's App Store.
Like Promptu's forthcoming ShoutOUT, dettaSMS lets Italian speakers dictate their text messages in fluent, natural speech, instead of typing on the iPhone's touch-screen keypad. Transcribed SMS messages can be reviewed, edited and appended to before being sent.
"dettaSMS is the world's first carrier-deployed voice-to-text SMS iPhone application," said Giuseppe Staffaroni, Promptu's CEO. "To insure privacy, security, and scalability, message transcription is completely automatic -- no human is involved."
dettaSMS is integrated with Telecom Italia Mobile's billing system and built on Promptu's network speech recognition (NSR(TM)) architecture for speed, accuracy and scalability. Promptu's fully automated speech recognition delivers high accuracy, low latency and unparalleled security. User privacy is assured because the real-time voice signal is never processed manually.
Nuance & IBM have announced an agreement they say will help further accelerate innovation in speech recognition solutions for enterprises, consumers and partners worldwide.
As part of this agreement, Nuance has been chosen as IBM’s Preferred Business Partner for speech technologies and related professional services and will complement IBM’s Industry Solutions portfolio.
The two companies will focus on deploying speech technologies for ten industries: automotive, banking, electronics, energy and utilities, healthcare and life sciences, insurance, media and entertainment, retail, telecommunications, and travel and transportation.
Featured Items
DAD & hostage to one of the country’s SMALLEST-biggest train fans - Full story
