Tag Archives: how to wreck a nice beach

TEDxManchester (13 Feb 2012): Best of!

15 May

2012 can easily be dubbed the year of TEDx for me, as by mid-February I had already attended two TEDx events! First up was TEDxSalford in late January, where I was just a mindblown attendee, and two weeks later it was TEDxManchester where I had the honour to be a speaker!

TEDxManchester took place on Monday 13th February this year at one of the iconic Manchester locations – and my “local” – the Cornerhouse.  Among the luminary speakers were people I have always been admiring, such as the radio Goddess Mary Anne Hobbs, and people I have become very close friends with over the years – which has led me to an equal amount of admiration, such as Ian Forrester (@cubicgarden to most of us).

Here are their respective talks at TEDxManchester 2012 for you to get a taste of the atmosphere at the event and of the impact of the ideas and the immediacy of the sentiments circulated!

Mary Anne Hobbs

Ian Forrester

 My TEDxManchester talk

I spoke about the weird and wonderful world of Voice Recognition (“Voice Recognition FTW!”): from the inaccurate – and far too often funny – simple voice-to-text apps and dictation systems on your smartphones, to the most frustrating automated Call Centres, to the next generation, sophisticated SIRI and everything in-between. I explained why things go wrong and when things can go wonderfully right. The answer is “CONTEXT”; the more you have of it , the more accurate and relevant the interpretation of user intention will be, and the more relevant and impressive the system reaction / reply will be.

Here is finally my TEDxManchester video on YouTube.

And here are my TEDxManchester slides.

The (Re)Tweets

(in reverse chronological order)

@ar3toul4ki 17 Feb

thanks for the #TEDxMCR piccie @cubicgarden! http://farm8.staticflickr.com/7050/6875061121_69555f7eb3_b.jpg @TEDxManchester

Cornerhouse @CornerhouseMcr 16 Feb

For those of you who missed #TEDxMCR check out @cubicgarden’s pics! Videos should be with us in a couple of weeks http://www.flickr.com/photos/cubicgarden/tags/tedxmcr/

Retweeted by @ar3toul4ki

Martin Williams @ukcopywriting 15 Feb

@ar3toul4ki ‘s Next level awesome epic bio – http://www.tedxmanchester.com/#speakers #TEDxMCR
Retweeted by @ar3toul4ki
In reply to @ar3toul4ki

@ar3toul4ki 15 Feb

What an awesome (wicked, epic) bio the cool guys and girls @TEDxManchester have written for me!!! http://www.tedxmanchester.com/#speakers #TEDxMCR

@ar3toul4ki 15 Feb
RT @global_lingo: Maria Aretoulaki on voice recognition software. Will digital transcription ever be any good? #tedxmcr no, no it won’t

Lynne McCadden @lmccadden 14 Feb
Belated I know but many congrats to @herbkim for a fantastic TEDxMCR yesterday been thinking about some of it all day today !
Retweeted by @ar3toul4ki

TEDxManchester @TEDxManchester 14 Feb
Here’s to the #TEDxMCR speakers in Session 2 – @daveerasmus @martinsfp @ar3toul4ki @cubicgarden @brendandawes
Retweeted by @ar3toul4ki

TEDxManchester @TEDxManchester 13 Feb
Thanks to @BandXMedia all today’s #TEDxMCR talks were recorded, will be edited & put online soon 🙂 #TEDxMCR @s2martin
Retweeted by @ar3toul4ki

Lynne McCadden @lmccadden 13 Feb

#tedxmcr learning about quarks and leptons from @tarashears making particle physics easy – sort of
Retweeted by @ar3toul4ki

Lynne McCadden @lmccadden 13 Feb

watching this @TEDxManchester kevin slavin’s TED talk on how algorithms shape our world:  http://www.ted.com/talks/kevin_slavin_how_algorithms_shape_our_world.html
Retweeted by @ar3toul4ki

Dr Marieke Navin ‏ @lisamarieke

depends if fitting gaussians to your data is your thing… Question is, do you understand your data?!
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki

Oh yes! © Bruce Balentine RT @LukeRobertMason: “It’s better to be a good Machine than a bad person” Discuss? #TEDxMCR
13 Feb
Luke Robert Mason ‏ @LukeRobertMason

How to Wreck a Nice Beach @TEDxManchester #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
Luke Robert Mason ‏ @LukeRobertMason

It’s a bright future if you are an algorithm or infomorph #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
Luke Robert Mason ‏ @LukeRobertMason

@RichardMichie A little bit of non-human agency can’t hurt… Or can it 😉 #TEDxMCH
Retweeted by @ar3toul4ki
In reply to RichardMichie
13 Feb
 Ian Forrester ‏ @cubicgarden 

Infomorphs or a weaver… #TEDxMCR love the idea 🙂 very cool! They could work with #perceptivemedia yfrog.com/gzeg2jij
Retweeted by @ar3toul4ki
13 Feb
Ian Pettigrew ‏ @KingfisherCoach

#TEDxMCR @skeuomorphology challenging ‘necessity is the mother of invention’; cars weren’t invented as a response to a shortage of horses!
Retweeted by @ar3toul4ki
13 Feb
Luke Robert Mason ‏ @LukeRobertMason 

Pure information technologies are the first evolutionary aware technologies. They are stochastic… Emerge from randomness #TEDxMCR @weavrs
Retweeted by @ar3toul4ki
13 Feb
Luke Robert Mason ‏ @LukeRobertMason 

Living software ‘bots’ or infomorphs via @weavrs #infomorph #TEDxMCR @skeuomorphology
Retweeted by @ar3toul4ki
13 Feb
Michael Di Paola ‏ @MichaelDiPaola

Robots made from programmable gel…where the hell am I? A parallel universe, the future. No. Just at #TEDxMCR listening to Dan O’Hara
Retweeted by @ar3toul4ki
13 Feb
 Luke Robert Mason ‏ @LukeRobertMason 

Infomorph, a form that exists just of information @skeuomorphology #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb

Luke Robert Mason ‏ @LukeRobertMason 

Another type of software agent that exhibits life, @weavrs #infomorph @skeuomorphology #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb

@ar3toul4ki 

@pgaval δε πειράζει, θα είναι στο YouTube για πάντα! (Μαμά! )
In reply to Petros Gavalakis
13 Feb

@ar3toul4ki 

Mondays are my favourite days of the week : D
13 Feb
 Matthew Brooks ‏ @brooksoid 

Great, great talk by @brendandawes on the value of pursuing ideas, and the ideas they spawn, without necessarily knowing where you’re going
Retweeted by @ar3toul4ki
from Manchester, Manchester
13 Feb
 RichardMichie ‏ @RichardMichie 

Failed art at school? You can still exhibit at #moma @brendandawes #tedxmcr great story love it
Retweeted by @ar3toul4ki
13 Feb
 @ar3toul4ki 

@brendandawes’ cinema redux of Hitchcock’s Vertigo #TEDxMCR twitpic.com/8jfs95
13 Feb

sphey1 ‏ @sphey1

If you make something, give it a name – re: Cinema Redux @brendandawes #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki 

Things that @brendandawes has done with his 3-printer #TEDxMCR twitpic.com/8jfpn6
13 Feb
 

@ar3toul4ki 

@brendandawes : the creative process is iterative. ( but Battling it against time & cost constraints) #TEDxMCR
13 Feb
@ar3toul4ki 

RT @CMindsKelly: @brendandawes. The thing we in the room all share is curiosity. That’s why we’re always making new things #TEDxMCR”
13 Feb
 Martin Bryant ‏ @MartinSFP 

At #tedxmcr, @cubicgarden explained how @tdobson and @adew saved his life. instagr.am/p/G9BmXRStoc/
Retweeted by @ar3toul4ki
13 Feb

@ar3toul4ki

Ian Forrester: fear the fear #TEDxMCR
13 Feb
 Claire-Marie ‏ @CMBoggiano

‘We are complex & unique organisms And yes, I am still an atheist.’ Ian Forrester, #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
 @ar3toul4ki 

Indeed! RT @TonyChurnside: @cubicgarden really touching. Very nicely done!
13 Feb
@ar3toul4ki 

@brooksoid any time!
In reply to Matthew Brooks
13 Feb
 Matthew Brooks ‏ @brooksoid 

@ar3toul4ki great talk Maria, speech recog in focus at the beeb right now, be interesting to talk once I’ve worked out what our landscape is
Retweeted by @ar3toul4ki
13 Feb
 TEDxManchester ‏ @TEDxManchester

Link to the funny vid played by @ar3toul4ki – Scottish voice recognition problems.. http://youtu.be/sAz_UvnUeuU

Retweeted by @ar3toul4ki
13 Feb
 @ar3toul4ki 

Ευχαριστώ! Το είδες μήπως; RT @pgaval: @ar3toul4ki Καλή επιτυχία!
13 Feb
 Claire-Marie ‏ @CMBoggiano 

‘When I was lying in bed dying, where were the real people?’ Ian Forrester, #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
 Tony Churnside ‏ @TonyChurnside 

Watching @cubicgarden talk about his #brushwithdeath. A very scary time. #TEDxMCR pic.twitter.com/hED5mimw
Retweeted by @ar3toul4ki
13 Feb

@ar3toul4ki 

@tdobson @cubicgarden is talking about you! : D
In reply to Tim Dobson
13 Feb
 Tim Dobson ‏ @tdobson 

so @cubicgarden is talking about it #brushwithdeath when I may or may not have been his flatmate at the time.. #tedxman
Retweeted by @ar3toul4ki
13 Feb
 Matthew Brooks ‏ @brooksoid 

And @cubicgarden ‘s talk is about… @cubicgarden ! He’s finally gone recursive. #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
 Tony Churnside ‏ @TonyChurnside

@cubicgarden you’re looking good! pic.twitter.com/n8xvkzJB
Retweeted by @ar3toul4ki
13 Feb
 Ian Forrester ‏ @cubicgarden

And next on at #TEDxMCR its @ianforrester. With the story of me…
Retweeted by @ar3toul4ki
13 Feb
 TEDxManchester ‏ @TEDxManchester 

Hilarious talk on Voice Recognition from Dr Maria Aretoulaki #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
 Tim Dobson ‏ @tdobson

@davemee it’s all about context! /cc @ar3toul4ki 😉
Retweeted by @ar3toul4ki
In reply to Dave Mee
13 Feb
 Tim Dobson ‏ @tdobson 

@davemee @ar3toul4ki “fetish cheese”
Retweeted by @ar3toul4ki
In reply to Dave Mee
13 Feb
 Dave Mee ‏ @davemee 

@tdobson @ar3toul4ki feed her through siri and send me a transcript!
Retweeted by @ar3toul4ki
In reply to Tim Dobson
13 Feb
 Kate Towey ‏ @katiemaymanc 

Fascinating talk from Tara Shears on particle physics. ‘2012 is year of the Higgs’ #tedxmcr
Retweeted by @ar3toul4ki
13 Feb
 Ian Pettigrew ‏ @KingfisherCoach 

So far at #TEDxMCR we’ve covered pursuing your passion, JDI (and make mistakes), technology, algorithms, and particle physics. I’m happy!
Retweeted by @ar3toul4ki
13 Feb
 Allie Johns ‏ @AllieJohns

I propose bringing back Tomorrow’s World and having Tara Shears present it #tedxmcr
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki

@TaraShears @TEDxManchester: oh my Higgs! We’ve seen something! Or have we?? #TEDxMCR twitpic.com/8jdo56
13 Feb

Ian Forrester ‏ @cubicgarden 

The goddamn particle explained at #TEDxMCR yfrog.com/obsv5tmj
Retweeted by @ar3toul4ki
13 Feb

@ar3toul4ki 

@TaraShears @TEDxManchester: where’s that God-damned Higgs particle?! If we don’t find it, we’ll have to start all over again… #TEDxMCR
13 Feb
 Claire-Marie ‏ @CMBoggiano 

“@lmccadden: #tedxmcr learning about quarks and leptons from @tarashears making particle physics easy – sort of”
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki

@TaraShears @TEDxManchester: symmetry, simplicity, elegance = beauty of the standard model of particle physics #TEDxMCR
13 Feb
 TEDxManchester ‏ @TEDxManchester 

Up next @TEDxManchester is @TaraShears – tune in live to ow.ly/92eRf #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
 @ar3toul4ki 

@TEDx video 1 @TEDxManchester: pragmatic chaos to describe fluid things such as culture #TEDxMCR
13 Feb
@ar3toul4ki 

@coralgrainger no worries sweetness : )
In reply to coralgrainger
13 Feb
@ar3toul4ki 

@TEDx video @TEDxManchester: what we don’t understand, we give a name and a story to #TEDxMCR
13 Feb
 @ar3toul4ki 

@maryannehobbs you were, nay ARE, awesome! Xx
In reply to maryanne hobbs
13 Feb
@ar3toul4ki

Dan O’Hara @skeuomorphology @TEDxManchester: from random relentless replication (cf. spambots) to guided transformation of chaos #TEDxMCR
13 Feb
 Kim Willis ‏ @KimberleyWillis 

Dan O’Hara: technology is not a selection of gadgets but a body of knowledge instagr.am/p/G8sGbrBVY7/ #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb

Ian Wareing ‏ @ianwareing 

#tedxmcr @skeuomorphology “Necessity is not the mother of invention. Invention is the mother of necessity”
Retweeted by @ar3toul4ki
13 Feb
 Ian Forrester ‏ @cubicgarden

Bloatware… or stimulation of the real on the virtual RT @maanasvarun: Skeumorphism. wait what? #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki 

Dan O’Hara @skeuomorphology @TEDxManchester: the creation of living technology by merging the Arts and Sciences #TEDxMCR
13 Feb
@ar3toul4ki 

@tombloxhammbe @TEDxManchester: go through life making mistakes, otherwise you don’t take any decisions, just do it ! © #TEDxMCR
13 Feb
@ar3toul4ki 

@maryannehobbs @TEDxManchester: John Peel saving lives again #TEDxMCR
13 Feb
@ar3toul4ki 

@maryannehobbs @TEDxManchester: follow your passion! #TEDxMCR twitpic.com/8jcwpn
13 Feb
 TEDxManchester ‏ @TEDxManchester

Hi all we’re suggesting #TEDxMCR as the hashtag for the event today as it’s a bit shorter than #TEDxManchester 🙂
Retweeted by @ar3toul4ki
13 Feb
 TEDxManchester ‏ @TEDxManchester 

Sorry folks for the livestream #fail. We’re currently on this channel live.. bit.ly/y9kkZa #TEDxMCR
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki 

@gazshaw cheers!
In reply to Gaz Shaw
13 Feb
@ar3toul4ki

😀 see you there Mike! It’s been a loooong time! RT @mike_higham: @ar3toul4ki @TEDxManchester Looking forward to it #TEDxMCR
13 Feb
@ar3toul4ki 

@heloukee oh nooo : s
In reply to Helen Keegan
13 Feb
@ar3toul4ki 

Excited & honoured to be speaking @TEDxManchester today. My talk “Voice Recognition FTW!” on the present+future of user interfaces #TEDxMCR
13 Feb
@ar3toul4ki 

See you there Matt! RT @matthbooth: A bit of work then @TEDxManchester. Looking forward to it.
13 Feb
 Allie Johns ‏ @AllieJohns 

“@maryannehobbs: interesting day: speaking about passion at @TEDxManchester 1pm.. ” > we can never have enough passion in our lives.
Retweeted by @ar3toul4ki
13 Feb
@ar3toul4ki 

😀 Will you be my groupie?? RT @technicalfault: @ar3toul4ki Dr Maria at TEDx!
12 Feb
@ar3toul4ki 

Looking forward to giving #TEDxMCR an insight into the wondrous+often misconstrued world of voice recognition @TEDxManchester tomorrow
12 Feb
 TEDxManchester ‏ @TEDxManchester 

And in other late-breaking news Dr. Maria @Ar3toul4ki will also be taking the stage tomorrow at #TEDxMCR 🙂
Retweeted by @ar3toul4ki
12 Feb
 TEDxManchester ‏ @TEDxManchester 

A big welcome for our latest speaker @MartinSFP – European Editor @TheNextWeb for #TEDxMCR. Like @MaryAnneHobbs a brave no-slide presenter!
Retweeted by @ar3toul4ki
11 Feb
 Anna Nachesa ‏ @ashalynd 

I’ll probably be very evil if I ask during an interview if tail-optimized recursion is possible in C. OTOH, it might be a great icebreaker:)
Retweeted by @ar3toul4ki
11 Feb
@ar3toul4ki 

RT @TEDxManchester: @ar3toul4ki:really excited bout Mons #TEDxMCR @maryannehobbs @brendandawes @cubicgarden @skeuomorphology @tombloxhammbe

10 Feb
@ar3toul4ki 

Can’t wait to finally meet you! : D RT @maryannehobbs: @ar3toul4ki 🙂

10 Feb
 @ar3toul4ki 

Getting really excited about Monday’s #TEDxMCR @CornerhouseMcr: @maryannehobbs @brendandawes @cubicgarden Dan O’Hara & my Uni’s Tom Bloxham

Speech Recognition for Dummies

20 May

OK, I often have to explain to people what I do and in most cases I get an enquiring and mystified look! What is Speech Recognition, let alone VUI Design! So I guess I have to go back to basics for a bit and explain what Speech Recognition is and what speech recognition applications involve.

What is Speech Recognition then?

Speech Recognition is the conversion of speech to text.  The words that you speak are turned into a written representation of those words for the computer to process further (figure out what you want in order to decide what to do or say next). This is not an exact science because – even among us humans – speech recognition is difficult and is fraught with misunderstandings or incomplete understanding. How many times have you had to repeat your name to someone (both in person and on the phone)? How many times have you had someone cracking up with laughter, because they thought you said something different to what you actually said? These are examples of human speech recognition failing magnificently! So it is no wonder that machines do it even less well. It’s all guesswork really.

In the case of machine speech recognition, the machine will have a kind of lexicon into its disposal with possible words in the corresponding language (English, French, German etc.) and their phonetic representation. This phonetic representation describes the ways that people are most likely to pronounce this specific word (think of Queen’s English or Hochdeutsch for German, at this point). Now if you bring regional accents and foreigners speaking the language into the equation, things get even more complicated. The very same letter combinations or whole words are pronounced completely differently depending on whether you are from London, Liverpool, Newcastle, Edinburgh, Dublin, Sydney, New York, or New Orleans. Likewise, the very same English letter combinations and words will sound even more different when spoken by a Greek, a German or a Japanese person. In order to deal with those cases, speech recognition lexica are augmented with additional “pronunciations” for each problematic word. So the machine can hear 3 different versions of the same word spoken by different people and still recognise it as one and the same word. Sorted! Of course you don’t need to go into all this trouble for every possible word or phrase in the language you are covering with your speech application. You only need to go to such lengths for words and phrases that are relevant to your specific application (and domain), as well as for accents that are representative of your end-user population. If an app is going to be used mainly in England, you are better off covering Punjabi and Chinese pronunciations of your English app words rather than Japanese or German variants. There will of course be Japanese and German users of your system, but they represent a much smaller percentage of your user population and we can’t have everything!!

Speech recognition may be based on text representations of words and their phonetic “translation” (pronunciations) but the whole process is actually statistical. What you say to the system will be processed by the system as a wave signal like this one here:

Speech signal for “.. and sadly crime experts predict that one day even a friendly conversation between mother and daughter will be conducted at gunpoint” 🙂  (Based on the Channel 4 comedy series “Brass Eye” – Season 1)

So the machine will have to figure out what you’re saying by chopping this signal up into parts, each representing a word that makes sense in the context of the surrounding words. Unfortunately the same signal can potentially be chopped up in several different ways, each representing a different string of words and of course a different meaning! There’s a famous example of the following ambiguous string:

signal for “How to Wreck a Nice Beach” err I mean “How to recognise Speech”!! (Taken from FNLP 2010: Lecture 1: Copyright (C) 2010 Henry S. Thompson)

The same speech signal can be heard as “How to wreck a nice beach” or .. “How to recognise speech“!!! They sound very similar actually!! (Taken from FNLP 2010: Lecture 1) So you can see the types of problems that us humans, let alone a machine, are faced with when trying to recognise each other!

Speech Recognition Techniques

The approach to speech recognition described above, which uses hand-crafted lexica, is the standard “manual” approach. This is effective and sufficient for applications that represent very limited domains, e.g. ordering a printer or getting your account balance. The lexica and the corresponding manual “grammars” can describe most relevant phrases that are likely to be spoken by the user population. Any other phrases will be just irrelevant one-offs that can be ignored without negatively affecting the performance of the system.

For anything more complex and advanced, there is the “statistical” approach. This involves the collection of large amounts of real-world speech data, preferably in your application domain: medical data for medical apps, online shopping data for a catalogue ordering app etc. The statistical recogniser will be run over this data multiple times resulting in statistical representations of the most likely and meaningful combinations of sounds in the specific human language (English, German, French, Urdu etc.).  This type of speech recogniser is much more robust and accurate than a “symbolic” recogniser (which uses the manual approach), because it can accurately predict sound and word combinations that could not have been pre-programmed in a hand-crafted grammar. Thus statistical recognisers have got much better coverage of what people actually say (rather than what the programmer or linguist thinks that people say). Sadly, most speech apps (the Interactive Voice Response systems or IVRs, for instance, used in Call Centre automation) are based on the manual symbolic approach rather than the fancy statistical one, because the latter requires considerable amounts of data and this data is not readily available (especially for a new app that has never existed before). A lot of time would need to be spent recording relevant human-2-human conversations and even more time to analyse it in a useful manner. Even when data is available, things such as cost and privacy protection get in the way of either acquiring it or putting it into use.

Speech Recognition Applications

By now you should have realised how complex speech recognition is at the best of times, let alone how difficult it is to recognise people with different regional accents, linguistic backgrounds, and .. even moods or health conditions! (more on that later) Now let’s look at the different types of speech recognition applications. First of all, we should distinguish between speaker-dependent and speaker-independent apps.

Speaker-dependent applications involve the automatic speech recognition of a single person / speaker. It could be your dictation system that you’ve installed on your PC to take notes down, or start writing emails and letters. It could be your hand-held dictation system that you carry around as a doctor or a lawyer, composing a medical report on your patients or talking to your clients, walking up and down the room. It could even be your standard mobile phone or smartphone / iphone / Android  that you use to call (voice dial) one of your saved contacts, search through your music library for a track with a simple voice command (or two), or even to tweet. All these are speaker-dependent applications in that the corresponding recogniser has been trained to work with your voice and your voice only. You may have trained it in as little as 5 minutes of speaking to it or longer / shorter in other cases, but it will work sufficiently well with your voice, even if you’ve got a cold (and therefore a hoarse voice) or you’re feeling low (and are therefore more quiet than usual). Give it to your mate or colleague though and it will break down, or misrecognise you in some way. The same recogniser will have to be retrained with any other speaker in order to work.

Enter speaker-independent speech recognition systems! They have been trained on huge amounts of real-world data with thousands of speakers of all kinds of different linguistic, ethnic, regional, or educational backgrounds. As a result, those systems can recognise anyone, both you and your mate and even all your colleagues or anyone else you are likely to meet in the future. They are not tied to the way you pronounce things, your physiology or your voiceprint; they have been developed to work with any human (or indeed machine pretending to be a human, come to think of it!).  So when you buy off-the-shelf speech recognition software, it’s going to work immediately with any speaker, even if badly in some cases. You can later customise it to work for your specific app world and for your target user population, usually with some external help (Enter Professional Services providers.). Speaker-independent applications can work on any phone (mobile or landline) and are used mainly to (partly) automate Call Centres and Helplines, e.g. speech and DTMF IVRs for online shopping, telephone banking or e-Government apps. OK, speech recognition on a mobile can be tricky as the signal may not be good, i.e. intermittent, the line could be crackling, and of course there is the additional problem of background noise, since you are most likely to use it out in the busy streets or some kind of loud environment. Speaker-independent recognition is also used to create voice portals, i.e. speech-enabled versions of websites for greater accessibility and usability (think of disabled Web users). Moreover, a speaker-independent recogniser is also used for voicemail transcription, that is when you get all the voicemails you have received on your phone transcribed automatically and sent to you as text messages, for instant and – importantly – discrete accessibility. They are B2B applications, which means that the solution is sold to a company (a Call Centre, a Bank, a Government organisation). In contrast, speaker-dependent apps are sold to an individual, so they are B2C apps, they are sold directly to the end customer.

Because speaker-independent apps have to work with any speaker calling from any device or channel (even the web, think of Skype), the corresponding speech recogniser is usually stored on a server or cloud somewhere. Speaker-dependent apps on the other hand are stored locally on your personal PC, laptop, Mac, mobile phone or handheld.

And to clear any potential confusion beforehand, when you ring up from your mobile an automated Call Centre IVR (for instance to pay a utilities bill), you are using a speech recogniser stored at that Call Centre’s, the company’s, reseller’s or solution provider’s server rooms. So in that case, although you are using your unique voice on your personal mobile phone, the recogniser does not reside on it. The same holds for voicemail transcription, curiously! Although you are using your unique voiceprint on your personal phone to leave a voicemail on your mate’s phone, the speech recogniser used for the automatic transcription of your mate’s voicemail will be residing on some secret server somewhere, perhaps at the Headquarters of their mobile provider or whoever is charging your mate for this handy service. In contrast, when you use a dictation / voice-to-text app on your smartphone to voice dial one of your contacts, your personal voiceprint, created during training and stored on the device, is used for the speech recognition process. So recognition is a built-in feature. Nowadays there is, however, a third case: if you are using your smartphone to search for an Indian restaurant on Google Maps, the recogniser actually resides in the cloud, on Google servers, rather than on the device. So there are increasingly more permutations of system configurations now!

There are many off-the-shelf speech recognition software packages out there. Nuance is one of the biggest technology providers for both speaker-independent and speaker-dependent / dictation apps.  Other automatic speech recognition (ASR) software companies are Loquendo, Telisma, and LumenVox.  Companies specialising in speaker-dependent / dictation systems are Philips, Grundig and Olympus, among others.  However Microsoft has also long been active in Speech processing and lately Google has also been catching up very fast.

The sky is the limit, as the saying goes!