By User:King of Wikis (Own work) [CC BY-SA 3.0], via Wikimedia Commons
I have been pondering the speech recognition question/opportunity for a while now and a recent QIAT listserv threaded conversation gave me the idea to share my ideas as well as others and some of the resources surrounding this topic.
The ability for computer-based devices to recognize speech is not something new, as a matter of fact, it’s been around for about six decades. Speech technology’s recent surge in popularity in education is further continuing this conversation and utilization.
My ideas and resources below are by no means the ONLY way to tackle speech recognition in the classroom. I just hope to share some ideas, questions and reflections from my experiences.
Before I even share an assistive technology tool with any teacher, I will have asked them to refer to the SETT Framework (developed by Joy Zabala and part of the IPP process in Alberta). Teachers need to consider who the student is as a learner, what the learning environment is like, what are the writing tasks and what tools can be used to remove the barriers in learning.
Speech recognition can work positively for those students who are able to express their thoughts and ideas better verbally than through writing or typing. If the student is already able to use or can learn the skills of proper enunciation, continual oral output (no hesitations), self-monitoring, patience and is motivated, then trying speech recognition may be a good choice for them.
I work most often with administrators and teachers in our school division; however I also happily work with students when the opportunity arises. The ability to take time to show some tools and resources that could make a difference to students is one that I hold near and dear to my heart. The fact that our school division has access to various low tech to high tech software, hardware and professional sharing opportunities has aided this along significantly.
Proper introduction to speech recognition tool(s)
- Now available
- Speaker-dependent speech recognition – creation of a personalized voice profile where the speaker must train the software program to recognize its voice such as Dragon Naturally Speaking (for PC) or Dragon Dictate (for Mac).
- Speaker-independent speech recognition – no profile creation, software picks up current voice such as Siri, Google Voice, Android. This is where I spend my time on laptops, netbooks and Chromebooks nowadays with: Google Docs add-on > Speech recognition. Our school division is three years into using Google Apps for Education (GAFE). Some of our schools have entered into Bring Your Own Devices and with all students have a GAFE account, this helps with staff and students working from the same cloud environment. There are many Google apps and extensions that can be used. The Google Docs add-on > Speech recognition opens up a right pane within a google document for the speaker to immediately use.
- Read&Write for Google chrome extension > Speech input is available for free for teachers and is a licensed product for students.
- Voice Note II chrome extension is available for free in the Chrome Web Store and once installed, when a user chooses it from their toolbar, Voice Note will pop up over top of any current work and you can start dictating away, copy the text and insert it anywhere you require!
- There are also iPads found in our classrooms and two popular recommended apps to try out are: Dragon Dictate and Paperport Notes iOS apps are both created by Nuance. Both are simple to use and Paperport offers a variety of note taking opportunities besides oral such as typing, handwriting, audio, inserting images, changes to paper types and exporting to GDrive (as well as other options).
- Think about the space where the dictation will occur. Is it loud? Can the student move to a quieter part of the classroom or to a space outside of the classroom?
- Think about the microphone. Is the USB microphone (on the device or the headset) extra sensitive to surrounding voices and/or noises? Some USB headsets that have been successfully used in the school division are:
- Part of a continuum of inclusive technologies where teachers and students can combine speech recognition with other software and applications like:
- GAFE with premium Read&Write for Google
- 30Hands iOS app
- Blogging with Edublogs and the EasyBlogjr iOS app
- ShowMe/Educreations iOS apps
- The Writing Process
- Students need to be able to compose orally which is different than writing with a pencil or typing on a keyboard.
- Give them time to practice and use scaffolding strategies to support writing such as pre-writing activities and editing.
- Using the tool – students will then use the speech recognition tool and through practice, they can either verbally process one sentence at a time (turning off the microphone in between) or on all out ‘verbal dump’.
- Once the dictation is completed, students can then edit and revise either using a keyboard or using speech recognition.
- One must remember that producing more text doesn’t equate to better writing but it does allow for more complex cognitive tasks like revision and reorganization of ideas.
- Speech recognition can be used for a variety of writing tasks such as:
- Sentence answering
- Essay writing
- Report/research writing
- 24 Years of Speech Recognition Work at ICSI
- Alternate to Dragon Dictation App conversation via the Quality Indicators for Assistive Technology (QIAT) listserv, week of February 22, 2015
- Four Ways to use Speech Recognition in Your Classroom
- Speech Recognition as AT for Writing
- Speech Recognition Software