Five learners at Queen Alexandra College in Birmingham have generously donated voice samples through the Nuvoic Project to support Voiceitt’s development of accessible speech technology. Many thanks to learners and the staff team at QAC for your support!
Nuvoic participant Conór interviews Voiceitt’s Product Specialist Michael Cash about his role with Voiceitt and how he uses their dictation app for work and in his personal life. They also talk about disability and assistive technology, as well as the really important questions: ‘Coffee or tea?’, ‘Crisps or chocolate?’ ‘Dog or cat?’ and ‘What made you smile today?’! This is the latest of a series of ‘Chat with Conór’ interviews, you can see the others on his YouTube channel: Conor O’Kane – YouTube. Great job Conór and thanks for sharing this!
In February 2023, our Technologist Geena Vabulas represented the Nuvoic team at the International Conference on Disability and Diversity. Our presentation was about our methods and results from the Nuvoic Project: how the Karten Network team has supported participants to test and share feedback on Voiceitt’s accessible speech technology, and contribute to their development work by donating speech samples. We knew she’d do a great job and the conference organisers agreed – awarding her Best Presentation in our group. Excellent work Geena and everyone!
Nuvoic participant Daniel Burgess, from Cheshire, has been testing Voiceitt’s original app for several months and has recently started to test their new dictation app. He shared the following photo and quote with Voiceitt, to help let people know about their technology and how it can help people with atypical speech. Great work Daniel!
Now into the final few months of the Nuvoic Project, our participants continue to make amazing contributions to the development of Voiceitt’s accessible voice technology. Having collectively submitted over 24,000 recordings to Voiceitt’s database of atypical speech, some participants are now starting to test Voiceitt’s new dictation tool, designed for users with dysarthric speech to transcribe their words in real-time.
Progress review: from single phrases to real-time transcription for spontaneous atypical speech
Since 2020, our team has supported people whose speech and communication is affected by conditions such as cerebral palsy, stroke, brain injury, Down’s syndrome and motor neurone disease, to test and help improve Voiceitt’s accessible speech recognition. Voiceitt supports communication and voice control of smart technologies, enabling users to be more independent and autonomous, and to have their voices heard.
Many of our early participants asked for more flexible recognition from Voiceitt – for the app to interpret whatever they want to say without having to stick to pre-trained phrases. In 2021 Voiceitt launched Ensemble, asking people with atypical speech to donate recordings to help work towards this goal. So far, 39 Nuvoic participants have registered and between them have submitted an incredible 24,000 recordings ?? Congratulations and a huge thank you to everyone who’s contributed!
During 2022, Voiceitt used these recordings to work on real-time recognition for spontaneous speech, as shown in this video: Voiceitt transcription demo video. While in the early stages, this is exciting progress with promising applications for in-person communication, captioning, dictation and device control. Our first few participants are now starting to test the transcription tool and we’re excited to see the results – watch this space!
We’re still accepting new participants, now including children under 13, so please get in touch if you or people you support would like to get involved. Please see our web pages or contact our project co-ordinator: email@example.com for more information.
In November the Nuvoic team attended the TechAbility conference in Birmingham. Project Co-ordinator Liz co-presented with AT Manager Dave Hursthouse from Leonard Cheshire, describing how our teams have collaborated to support residents at Hill House Care Home take part in Nuvoic. We spoke to lots of delegates about the project at our exhibition stand and saw some great presentations from other organisations.
In December, Voiceitt’s Customer Service Manager and Speech Therapist Rachel Levy was interviewed about Voiceitt’s latest developments by the Indata Project for their Assistive Technology Update podcast.
As Nuvoic draws to a close in April, we’ll be sadly losing our two Project Technologists, Sean Connolly and Geena Vabulas, at the end of February. Sean and Geena have made a huge and much-valued contribution to the project over the past two years, delivering excellent support to participants, families and support teams, and helping to promote and disseminate our work in many different settings. Both are moving on to exciting new roles where we wish them every success. Thank you both for playing such key roles in Nuvoic, you will be much missed by the Karten team and all those you’ve worked with!
Get in touch!
We would love to hear from you if you, or someone you know may be interested in taking part in donating speech samples or testing Voiceitt’s technology. Please email our project co-ordinator: firstname.lastname@example.org, or you can find more information and get in touch via our project web pages.
Here’s a quick video to wish everyone very happy holidays ⛄ ❄️ and a happy New Year ?. Many thanks to our participants Conór and Dan for joining in with us this year! With best wishes from all at the Karten Network.
On 16th November the Nuvoic Project team attended the TechAbility conference in Birmingham.
Project Coordinator Liz and AT Manager Dave Hursthouse from Leonard Cheshire gave a talk about how two Leonard Cheshire residents have been testing the Voiceitt app and donating speech recordings to help Voiceitt develop their new dictation tool.
We had lots of visitors to our stand and the photos and video clips of our participants really helped to show off everybody’s fantastic work and encourage new participants to join. Thanks to everyone involved for giving us so much to talk about!
Our Technologist Sean has made a super spooky video showing some spooktacular Alexa commands. Please email email@example.com if you would like any details about how he set these up. Wishing everyone a very spooky Halloween from all at the Karten Network!
Now into our third and final year of the Nuvoic Project, we’re seeing exciting progress in Voiceitt’s work on automatic speech recognition for atypical speech, and significant developments on their new dictation and captioning tool. Results are at an early stage, but they look promising!
Continuous recognition of atypical speech
Voiceitt’s app already supports people with atypical speech to communicate and control Smart Home technologies more easily, but users currently have to train each phrase in advance. In the next release, Voiceitt aims to offer real-time recognition to transcribe users’ speech without the need to pre-train every phrase.
To achieve this Voiceitt have launched Project Ensemble, a website where volunteers can donate recordings of atypical speech patterns as training data for Voiceitt’s recognition models. Through Nuvoic, we’ve been recruiting participants, offering support to take part and gift cards as a thank you for all contributions. So far the Karten team has supported 28 people to join Ensemble, who have uploaded an amazing 15,000 phrases in total – congratulations and thank you to everyone who’s contributed so far! ??
Voiceitt are already using these and recordings from other participants around the world to develop a new dictation and captioning tool. In the video below, Michael demonstrates his personal speech model providing live captions through Zoom (Zoom’s built-in captioning doesn’t work for Michael’s speech). Users can also dictate text to use in messages or documents, or to share onscreen with a conversation partner. While this technology is still at an early stage it’s a significant improvement on what’s currently available, and with more recordings will become more accurate over time.
However, we still need more participants to donate recordings to help develop this technology more quickly and test the results. We want to include as many non-standard voices as possible so please get in touch if you or people you support would like to get involved. We can offer equipment on loan, technical support, gift cards of up to £100 for participants and funding for organisations and individuals supporting someone to take part. If you or your organisation would like to be involved in this exciting development work, please see our web pages or contact our project co-ordinator: firstname.lastname@example.org for more information.
Feedback from users
As well as their work on continuous recognition, Voiceitt continue to use feedback from our participants to improve their app. Recent additions include: a button to flag misrecognitions, helping to improve accuracy; the option to repeat spoken output; and more options to use Bluetooth accessories in combination with the internal mic and speaker, to support the use of Voiceitt ‘out and about’ or in noisy environments. All of these features have been requested by users and it’s great to see them now available!