Voice to text recognition (for mobile)

Leave a comment

 HTC Smartphone Picture from BBC News

Ollie Bray writes another thought provoking post about technologies that will change how we live, work, play and learn, this time focusing on voice recognition software. As I have ranted on recently, this software has not been reliable or appropriate for many people in school.

Ollie writes:

But now there seems to be the very real prospect of converting speech to text on many mobile ‘phones’ very soon.

I know that very soon whether it is an android powered phone, an iPhone or a Windows phone most smart phones will have the capacity to translate the spoken word to text with a high degree of accuracy (in fact they can already do this).

If we accept that most mobile devices will be smart phones in the not to distant future and we also accept that most young people in Europe, North America, Australia, parts of Asia and a lots of other places in the world have mobile phones. Then we must also accept that it won’t be long until young people realize that they only have to speak into their devices to get them to write for them.

Ollie raises the pertinent question of whether there is really any need to get children to use pens and paper at all. This is certainly a perennial debate for those of us whose main agenda is to consider the learning needs of students with dyslexia and other reading difficulties.

It is clear to many of us, in Ollie’s words, that ‘never before in the history of communication during the last 100 years has it been even more important than ever to make sure children have a real grasp of the spoken language.’ This is one of the reasons why he (and I) are ‘delighted that our radical new curriculum in Scotland includes the spoken word as a type of ‘text’. Thank goodness it does as it is the only way that I can think of, to really future proof language.’

Adopting such new technologies such as speech to text recognition requires as much training as does learning to write accurately and automatically.

I know a couple of people whose grasp of the language is so powerful and whose thought processes are so refined that they can give a considered, fluent and beautifully polished response to a stimulus first time round.

The rest of us mumble, backtrack, contradict ourselves, or are just muddled in our thinking aloud (or is this just me?). We include circumlocutory devices and fillers (um, er, you know, like) and occasionally, with any luck and a fair wind behind us, form complete sentences. An accurate transcription of our speech is likely to need much editing before it can be regarded as coherent and easily understood by others.  Actually I don’t know what I think about very much at all until I write it down or hear myself speaking about it. Perhaps this is just me.

So to expect an app to be an easily accessible substitute for the written word is naïve. (By the way, I am not accusing Ollie of naivety – he is just the messenger). But it is imperative that we consider its advent.

Ollie concludes his interesting post thus:

I think this will be a significant paradigm shift in the way children engage with text and we are within 12 months of the tipping point for secondary / high school students and maybe 24 – 36 months away from the tipping point for elementary / primary school children. Teachers and leaders in schools need to be ready to embrace change and not be reactive to it or fight it (you will lose). Soon most children will have one of these devices and we can’t stop it. Things are about to move very quickly, are you, your school and your authority ready? 

What do you think?

 

 

 

Advertisements

Voice recognition software? Eat your heart out!

Leave a comment

I couldn’t resist this April Fool’s joke from Google even though I said I’d finished ranting about voice recognition software.

Great.

A good way to start the holiday.

A Final (I hope) word on voice recognition software

2 Comments

I have spoken with representatives from both Enquire and the ASN Division of the Scottish Government Both are very clear that their role is not to give advice to parents on specific supports but to provide information about the Additional Support for Learning Act 2004. They were apologetic.

They defend themselves by saying that any specific enquiry is always greeted by a recommendation to parents that they contact their school.

The advert that appeared last week was written by the Government’s marketing department with reference to the Code of Practice which was agreed after consultation with professionals across Scotland. Here is Chapter 2, paragraph 13:

13. Examples of additional support provided from within education services to children and young people are the following:

  • a support for learning assistant supporting a child with an autistic spectrum disorder in a nursery
  • class teacher helping a child by following a behaviour management programme drawn up in consultation with a behaviour support teacher
  • tutorial support from a support for learning teacher to help with a reading difficulty
  • use of communication symbols by a child with autism
  • designated support staff working with Gypsy/Traveller children on their site to help them improve their literacy and numeracy skills
  • in-class support provided by an English as Additional Language ( EAL) teacher for a child whose first language is not English
  • a more able child at the later stages of primary school receiving support to access the secondary mathematics curriculum
  • use of voice recognition software by a child with dyslexia.

Yes, the contentious software is mentioned right at the very end. I am most curious to know which professionals working in the field of dyslexia in Scotland felt that this was the most commonly used and widely regarded example of good practice. (And, no, I didn’t contribute to the consultation about the draft Code so I must take some responsibility for the erroneous, or at least heavily biased,  information being purveyed by the government and Enquire. There’s a lesson there.).

In my rough and ready estimate, about 1% of 15 – 18 year olds may be enabled to express themselves more effectively with voice recognition software; while about, ooh, 90% of learners with literacy difficulties are already benefitting from using WordTalk – a free resource developed in Scotland, available to families at home at no cost and easy to use.

I was given an assurance that in future other more frequently deployed supports will be offered as examples, although the ‘Just Ask’ campaign is now drawing to a close.

While I appreciate the civil servant’s acknowledgement that the use of this example was ill-advised, this does not help us to support those parents who feel that we have let them down by not offering this software as a matter of course. It is natural that parents will want the very best provision for their children; that’s their job. But to set them up for almost inevitable disappointment, and create conflict where none need be, negates the whole notion of partnership and calls into question teachers’ knowledge and understanding of dyslexia and the plethora of provisions we already successfully make.

(A piece of) Humble Pie

6 Comments

I was at a meeting yesterday with the parents of a 9 year old boy whose dyspraxia and dyslexia are so severe that he has immense difficulty expressing himself on paper or with a computer. He benefits from using mind mapping software to help planning and organisation and, while using a digital voice recorder quite efficiently, prefers to have a person to help him to order his thoughts and scribe his responses. He is exceptionally thoughtful, has a wide general knowledge and interest in many things and a very highly developed sense of his own strengths and difficulties.

In a personal project about dyslexia and dyspraxia he declares that

even if I could get the dyslexic and dyspraxic bits out of my DNA I wouldn’t as it makes me creative and who I am. I have learned lots of coping strategies aand have been given lots of help to get around the things I find tricky… I might invent something amazing when I’m older because I have great ideas.

His parents showed us the above video made by a 16 year old, Rhodri Buttrick, explaining how voice recognition software has enabled him to study. His story really seems extraordinary and it may be that this support will work for this particular pupil with his specific range of challenges and abilities and supports from home too.

The CALL Centre on speech recognition software

Leave a comment

Speech recognition software has been presented as a panacea for pupils with writing difficulties, but the reality can be very different! While there are a few schools where speech recognition has been used with pupils with great success, there are many more where it has been tried and quickly abandoned.

The CALL Introducing Speech Recognition in Schools project aimed to investigate best practice in schools where speech recognition was being used successfully, and develop and evaluate training materials to help other schools get going with speech recognition. It was funded by the Scottish Executive Education Department.

The main outcome of the project was a Training Pack (comprising a book and a CD) for schools to use when introducing speech recognition in schools. Copies of the books and CD were sent, free of charge, to all secondary schools in Scotland in March 2003. The pack includes:

  • Guidance on identifying pupils who might benefit from speech recognition;
  • Technical hints and tips on installing and operating the systems;
  • 10 Lesson Plans, with exercises, for introducing speech recognition to pupils;
  • Advice on management of speech recognition systems in schools.

The Pack was evaluated by 40 secondary schools in Scotland from November 2000 to March 2002, and modified in response to comments from staff and students. We chose to focus on Support for Learning Departments in secondary schools, rather than special schools or units, because the largest potential group of students are those with specific learning difficulties in secondary education.

Training Packs

Below are links to these training packs:

Thanks to S O’Neill through the ASN Glow Group for this link.

Voice Recognition software 2

3 Comments

I am still going on about the ‘Just Ask’ campaign about the suggestion that ‘a pupil with dyslexia may benefit from use of voice recognition software’.

As I wrote in my last post, I feel this is a most unhelpful statement, practically guaranteed to set parents in opposition to schools. Focusing on this one area that is, as  as I understand it, the least well regarded and least used support is staggering. There are so many supports we can and do offer to children with literacy difficulties in schools that to name this one, in my view erroneously, seems designed to cause friction between those parties who have the interests of the children most at heart: their parents/carers and their teachers.
The British Dyslexia Association has a very comprehensive summary of ICT supports for learners with dyslexia. It includes a useful list of focused questions to help audit diverse learning needs and map provision planning.

The paper summarises the supports that will be familiar to most of us who work in schools with learners with literacy difficulties.

At the very bottom of page 6 comes a reference to voice recognition software (look closely):

Offering alternatives to writing as key method of recording.

Dyslexic learners enjoy using alternative forms of recording [I loathe such blanket descriptions, but hey ho] and often use strengths in pictorial imagery in their learning. ICT can support this with the use of digital images and clip art, digital cameras, multimedia presentations and video cameras for example.

Recorded speech using tapes, minidisk or digital recorders offer low tech solutions.

Voice recognition software may be appropriate in some cases, especially at KS 3/4 where the demand for writing in all curriculum areas increases both in volume and difficulty.

I am awating a reply from Enquire Scotland as to their reasons for the inclusion of their misguided information. I am hoping that they can direct me to some research and/or practitioners who have found voice recognition software the most indispensable support for learners with dyslexia. I would be delighted to have my mind changed!

Why don’t you write too?

Voice recognition software

Leave a comment

The ‘Just Ask’ campaign from the Scottish Government urges parents to ask for help for their children ‘to help them navigate their way through issues affecting them’: these issues include dyslexia.

The advert in the local paper declares: ‘Support can be provided in many different ways and is entirely individualised to the child. For example, a pupil with dyslexia may benefit from use of voice recognition software’.

Oh dear. While I am in compete agreement that young people with dyslexia need a ‘plan to ensure success’, to be so specific about such a very difficult area as speech to text software is going to cause all sorts of genuine problems for us in schools. I can hear the parents bashing my door down as I write.

I have not used voice recognition software myself nor have I seen it in action. There are mostly good reviews here  but none focus on its deployment in schools.

The only review I can find that specifically mentions voice recognition software and young people  was last updated in December 2006. There may, of course, have been considerable changes for the better since then. I’d be grateful if anyone with knowledge and experience in this area would join the discussion.

I have tried to summarise the major points in that review as far as they relate to enabling youngsters to circumvent the barrier of writing. I have put my comments in brackets). The article does state that: ‘where spelling, handwriting and composing are major problems, then Speech Recognition can be hugely liberating and allow children to express their ideas on paper fluently for the first time in their lives’. Studies have shown that students with learning difficulties who use speech recognition:

  • Use longer and richer words
  • Write more creatively
  • Organise work better
  • Complete more work
  • Improve reading
  • Improve spelling
  • and produce better hand-written work’.

‘A ‘normally clear speaker [and here they are referring to adult users], using a recent computer with a decent microphone and with a little experience should get very good recognition results and gain real productivity benefits’. (My emphasis).

However, there are also many caveats, summarized thus:

  • Motivation is a key component. It would be impossible for children to learn dictation at the same time as learning the basics of computing, of Windows and of word processing. This all adds up to considerable information overload and time implications. On the whole children don’t produce masses of written work, so are less likely to have the motivation to persevere with speech recognition. If it’s not used often the child will need to relearn it each time; and is likely to stop bothering.
  • Patience and accuracy are needed. Time training the software to recognise the voice is necessary.[ And in young people, especially boys, the voice can change, requiring frequent up-dates]. Accuracy is hugely important. Each ‘mistake’ [or misinterpretation by the computer] made takes many times longer to correct compared with dictating a word correctly. [Children with ‘regional accents’ – i.e. accents from areas outside the south of England – are likely to find training the software to recognise their voices even more difficult].
  • Fluent speakers with a wide vocabulary are most successful at using speech recognition software. [Not all learners with dyslexia fall into this category].
  • Good, fast word retrieval, finding the words needed easily to express ideas, is essential. Multi-tasking – using the software whilst composing text – is also likely to be hard for many children with dyslexia. [Slow processing speed and poor automaticity are very common characteristics].
  • An understanding of word processing & punctuation is crucial. [No comment necessary].
  • A quiet, relatively private environment for confident dictation for training and using the software is not always available in busy classrooms.
  • Proof reading is particularly difficult for dyslexic people. They are liable to have more difficulty finding and correcting an error than somebody who reads and spells well. Even the best dictation system, after you have spent a long time training it and working with it, will make recognition mistakes.
  • Ongoing support is essential and this has implications for training for those who work with the child. For somebody new to dictation there are a lot of things to get right: diction style, microphone adjustment and positioning, making corrections, punctuation and the voice commands. Modifications to speech style (pace, clarity, particularly of unstressed words, evenness of volume) make a big difference.

The review stresses that, while a helpful resource in many instances, Speech Recognition software ‘can still lead to frustration and a lack of success. The main reasons for this will be human, not technical’. However, there are inevitably technical issues that would need to be addressed if adoption of the software is to be effective:

  • The microphone that comes with the software is universally derided. A better microphone than that supplied in the box may make the difference between success and failure. In addition, it is absolutely critical to have the microphone properly adjusted, and the authors of the review suspect that this is the single most likely cause of frustration and failure at dictation.
  • It is generally the case that a laptop computer will be slower and noisier than a desktop machine of the same specification although both might be so slow as to be virtually unusable. It follows that it is all the more important (and, consequently all the more expensive) to have more than the minimum spec if you want a computer to perform well. It is safer to choose a machine that has been certified for use with speech recognition. [In an ideal world schools would up-date their hardware to demand but this is unfeasible].

This makes for depressing reading as I know we would dearly love to find the miracle solution to the problem so beautifully described by one girl I know: ‘I can write 3 sentences, but speak 3 pages’. Alas, it seems that voice recognition software is not the panacea claimed in the adverts.

 I feel that the ’Just Ask’ team has performed a severe disservice to schools and parents in promoting this as a ‘support’ so thoughtlessly.

(I was also somewhat bewildered by the case study of a boy with dyslexia on the Just Ask site. It stated, ‘Jamie was offered a place at a literacy unit’. Do any of these exist nowadays? What about the philosophy of Inclusion and Equality? I feel another post coming on.)