Programming P{erl; with Vista Sp>eech@

Sometimes it's ok to sit back, take stock of where we are at, and allow our sense of humour to breathe.

All of us in the speech industry are keen to demonstrate and remind our clients and prospective clients that speech recognition has finally come of age and delivers tangible returns and savings in processing calls. And it does.

But it's easy to get a bit blinkered from time to time and forget the image speech recognition has in social consciousness; the consumers' experience of the technology is often different from the experience the industry promotes (and, on the whole, delivers).

This video is both painful and funny on several levels. It is painful to see someone struggle like this, but also painful to think the speech industry still has to overcome this kind of experience. It's funny because - well, let's face it - someone else's plight is usually pretty funny. But also the results are so predictable yet so obviously unintended.

But it highlights really nicely just what the challenges are of providing intuitive speech interfaces to "everyday" activities.

Even I was swearing at it half-way through, and I wasn't even there....

White noise can increase speech recognition accuracy

A recent study conducted at the University of Maryland Medical Center found that the introduction of white noise at certain levels as part of the acoustic background increased accuracy of speech recognition systems’ transcription capabilities. On the basis of their research, the scientists believe that the presence of low-level white noise significantly improves speech recognition accuracy, while higher levels may increase transcription error rates.[click heading for more]

Nuance Speech Now Available through Ford SYNC in Twelve 2008 Ford, Lincoln and Mercury Models

Nuance Communications, Inc. (Nasdaq: NUAN) today announced that Nuance® speech solutions are being shipped within Ford SYNC™ for twelve Ford, Lincoln and Mercury models for 2008. SYNC, a new factory-installed, in-car communications and entertainment system, is designed to change the way consumers use digital media portable music players and mobile phones in their vehicles.

This Ford-exclusive system, developed in conjunction with Microsoft and Nuance, includes Nuance speech technologies that provide consumers with the ability to bring nearly any mobile phone or digital media player into their vehicle and operate it using voice commands or the vehicle’s steering wheel or radio controls. SYNC seamlessly integrates the vehicle with the popular portable electronic devices of today and is expected to support future devices and services. [click heading for more]

Philips adds to language portfolio for healthcare speech recognition

Royal Philips Electronics has announced the launch of two new languages for its healthcare speech recognition technology SpeechMagic. By adding English for the Canadian market and Slovenian to its portfolio, SpeechMagic now supports 25 recognition languages, which will further expand the technology’s integration with healthcare IT systems worldwide. [click heading for more]

How voice recognition software can wreck a nice speech

You may or may not know that the BBC uses speech-to-text systems to produce the incredible amount of stuff on its website. But though we're sure that real humans also look over the stuff before it goes out, one rule that sub-editors tend to stick to, diligently, is not to change things in quotes.

But it isn't always perfect... [click heading for more]

Thomas Cook deploys speech recognition for holiday balances

Thomas Cook is offering its customers an automated speech recognition service to pay their outstanding holiday balances.
Thomas Cook is using a system from Fluency Voice Technology.
It has deployed the Fluency VSA speech recognition application suite to provide an automated service that enables its holiday customers to pay the outstanding balances on their holiday at any time of the day.
Holiday balance payment calls were identified by Thomas Cook as straightforward transactions that could be automated using speech recognition technology, freeing up agents for more complex, time-consuming enquiries. [click heading for more]

HP Enhances OCMP

HP today announced an enhanced media platform to help telecom operators accelerate growth. The HP OpenCall Media Platform 4.0 is a carrier-grade media server that handles call connections and the special digital processing that is required for services offering multimedia content, such as rich video and advanced messaging in social networking communities. [click heading for more]

Solving your Outlook contact woes

This post isn't strictly on topic for the blog, but it's my blog so I can break my own rules. Anyway - I figured this was too useful not to share!

For the last month or two I've been plagued by my Outlook contacts folder containing incomplete records, duplicates, missing email addresses, even as many as four versions of the same contact. This has been a real headache, and with the number of contacts reaching many many hundreds, fixing it by hand has been almost impossible.

The situation arose due to my change of employer. I exported my old contacts from outlook and re-imported them into my new instance - but even this process didn't work properly - some fields got lost, others mangled. It really was disappointing. On top of that, I hadn't realised that contacts I'd added from my old employer's Global Address list simply did not resolve to a set of complete details (most notably email addresses were missing).

To compound this, I then had the bright idea of trying to synchronise contacts across all my devices and domains - mobile phone, PDA, personal PC (using Outlook express) with PLAXO as the 'glue'. Sure, I got all my contacts in one place, but it created a mess.

For over a month I've been occasionally hand-fixing the odd record here and there, and looking on the web to find something to make the job easy. Amazingly Microsoft has no such tool to help - amazingly there is even no "find duplicates" function in Outlook, which alone would help helpful.

Then I found "duplicate killer" by 4team.

This wonderful bit of software is more powerful than its name suggests. As well as being able to identify and "kill" duplicates, perhaps more usefully it is able to merge records. You can do this fully automatically (identifying duplicates any way you choose, e.g. by names, by email etc.) or you can work through the gathered list of duplicates step-by-step, manually changing the fixes that the tool suggests. I have to say, so far I have found I am only having to change about 5% of the suggestions - but being the cautious type I am sticking with the manual preview.

The tool can also do similar tricks on your inbox and calendar - perhaps not something you would use quite as often, although non-the-less still useful (I do sometimes end up with duplicate appointments where both I and someone else create an appointment for the same meeting).

I thoroughly recommend "duplicate killer" if your Outlook contact database needs a good spring clean.

Reading Eagle Deploys VoicePort's CircPort OnDemand

Reading Eagle Company of Reading, Pensylvania has successfully deployed VoicePort's hosted speech application CircPort onDemand™, to field circulation phone calls. The family-owned Eagle has a daily circulation of 59,550. CircPort is completely integrated with the newspaper's DTI/PBS circulation database for real-time transaction processing.

VoicePort's hosted solutions provide smaller newspapers with the opportunity to implement a self-service speech recognition application without the associated capital expense. The Reading Eagle can now offer subscribers instant access to their account to schedule vacation holds, report delivery problems, make account payments, and more. [click heading for more]

Google And Microsoft Want To Hear From You

Google (GOOG) , and online rival Microsoft Corp., are using their free directory services to build vast, digital Petri dishes loaded with samples of users' speech patterns. Those patterns are in turn are being fed into the companies' myriad server computers, where they are analyzed in an effort to make their respective speech recognition technologies progressively smarter. The development of increasingly precise speech recognition technology begs the question of whether Google and Microsoft will one day use it to "listen" to users, in order to serve them relevant advertising -- likely raising privacy concerns. [click heading for more]