Macsen is an open source Welsh language voice assistant similar to Alexa or the Google Assistant. Open source means that anyone can see, adapt and distribute its code as they wish. It works as an app for phones and tablets, and is available for iOS and Android devices. An online version is also available here. You can speak in Welsh to Macsen to ask it to do various tasks or provide information.
Its growing set of skills include the ability to play Welsh Language music through Spotify, programmes through S4C Clic, turn the light on or off, get the news and weather, use ChatGPT, translate spoken English to Welsh text and transcribe Welsh speech to text.
We are using this project to show what we can create when developing Welsh language speech technology and artificial intelligence. We publish relevant components and resources with open licences on the Welsh National Language Technology Portal, so that other developers can also use them. We are also undertaking further research to improve it, and to enable it in other environments.
VIDEOS OF MACSEN
To see demonstrations of Macsen, watch the videos below:
DETAILS OF MACSEN’S SKILLS
Macsen takes the news from the Golwg360 website, and you can ask it for the headlines, news from Wales, Britain or international news, and news about business, sport, health.
The music comes from the Spotify website. At the moment it recognises 21 bands and individuals, namely Alffa, Anhrefn, Anweledig, Bryn Fôn, Cadi Gwen, Gandelas, Cowbois Rhos Botwnnog, Cyrff, Gwibdaith Hen Frân, Gwilym Morus, Lleuwen, Mellt, Melys, Petrobas, Plant Duw, Sibrydion, Sŵnami, Y Bandana, Y Cyrff, Yr Ods, Yws Gwynedd. If you do not have a Premium Spotify account, it will sometimes play related music, rather than what you asked for – this is a feature of Spotify’s free accounts, and is not a speech recognition error.
The weather comes from OpenWeatherMap.
Macsen uses ChatGPT-4 Language Model.
WELSH LANGUAGE TECHNOLOGIES WITHIN MACSEN
Macsen uses a number of different technologies to operate. It uses speech recognition to convert what you say into text. Then it uses intent parsing to recognise whether you asked for the news, weather, music or one of the other options. When Macsen needs to reply orally, it uses text-to-speech technology to speak the the appropriate response.
The app’s source code is available on GitHub as hopefully a useful resource for other developers:
Also , the source code for the app’s intent parser is available on GitHub:
Macsen is funded by the Welsh Government, and we thank them and the volunteers who have been contributing their voices to improve speech technology. Thanks also to Golwg360 and OpenWeatherMap for permission to use their online services.
Macsen Research Publications
Macsen: A Voice Assistant for Speakers of a Lesser Resourced Language, Proceedings of the 1st Joint SLTU and CCURL Workshop (SLTU-CCURL 2020), pages 194-201 Language Resources and Evaluation Conference (LREC 2020), Marseille, France Paper
Building Intelligent Assistants for Speakers of a Lesser-Resourced Language, CCURL 2016 2nd Workshop on Collaboration and Computing for Under-Resourced Languages ‘Towards an Alliance for Digital Language Diversity’ (LREC 2016), Portoroz, Slovenia. Paper
Towards a Welsh Language Intelligent Personal Assistant, A brief study of APIs for spoken commands, question and answer systems and text to speech for the Welsh Government. 2015. Report