Mycroft (software)

Mycroft is a free and open-source software voice assistant that uses a natural language user interface.[2][3][4] Its code was formerly copyleft, but is now under a permissive license.[1] It is named after a fictional computer from 1966 science fiction novel The Moon Is a Harsh Mistress.[5]

Mycroft
Developer(s)Mycroft AI team
Repository
Written inPython
LicenseApache License [1]
Websitemycroft.ai

History

Inspiration for Mycroft came when Ryan Sipes and Joshua Montgomery were visiting a makerspace in Kansas City, MO, where they came across a simple and basic intelligent virtual assistant project. They were interested in the technology, but did not like its inflexibility.[6][7] Montgomery believes that the burgeoning industry of intelligent personal assistance poses privacy concerns for users and has promised that Mycroft will protect privacy through its open source machine learning platform.[8]

Mycroft AI, Inc., has won several awards including the prestigious Techweek's KC Launch competition in 2016.[9] They were part of the Sprint Accelerator 2016 class in Kansas City and joined 500 Startups Batch 20 in February 2017.[10][11] The company accepted a strategic investment from Jaguar Land Rover during this same time period.[12] The company had raised more than $2.5 million from institutional investors before they opted to offer shares of the company to the public through StartEngine, an equity crowdfunding platform.[13]

Software

Mycroft voice stack

Mycroft provides free software for most parts of the voice stack.

Wake Word

Mycroft does Wake Word spotting, also called keyword spotting, through its Precise Wake Word engine.[14] Prior to Precise becoming the default Wake Word engine, Mycroft employed PocketSphinx. Instead of being based on phoneme recognition, Precise uses a trained recurrent neural network to distinguish between sounds which are, and which aren't Wake Words.

Speech to text

Mycroft is partnering with Mozilla's Common Voice Project to leverage their DeepSpeech speech to text software. [15]

Intent parsing

Mycroft uses an intent parser called Adapt to convert natural language into machine-readable data structures. Adapt undertakes intent parsing by matching specific keywords in an order within an utterance. They also have a parser, Padatious. Padatious, in contrast, uses example-based inference to determine intent.

Text to speech

For speech synthesis Mycroft uses Mimic, which is based on the Festival Lite speech synthesis system.[16]

Modular design and interoperability

Mycroft is designed to be modular, so users are able to change its components. For example, espeak can be used instead of Mimic.[17][18][19][20]

Hardware
Prototype of the Mycroft Mark II voice assistant

The Mycroft project is also working on and selling smart speakers that run its software. All of its hardware is open-source, released under the CERN Open Hardware Licence.[21]

Its first hardware project was the Mark I, targeted primarily at developers. Its production was partially funded through a Kickstarter campaign, which finished successfully. Units started shipping out in April 2016.[22]

Its most recent hardware project is the Mark II, intended for general usage, not just for developers. Unlike the Mark I, the Mark II is equipped with a screen, being able to relay information both visually as well as acoustically. As with the Mark I, the Mark II's production was partially funded through a Kickstarter campaign, which wrapped up in February 2018, hitting almost 8 times its original goal. In April 2020, the Mark II has not yet been delivered to crowd-funders.[23]

Mycroft announced that a third hardware project, Mark III, will be offered through Kickstarter, and that an entire product line of Mark I, II, and III will be released to stores by November, 2019.[24]

Partnerships

Mycroft has undertaken several commercial collaborations. In May 2018, the company partnered with WorkAround, an impact sourcing provider who broker work opportunities for refugees, to undertake bulk machine learning training.[25] In October 2018, Mycroft collaborated with disease surveillance and forecasting company, SickWeather, to identify the frequency of coughing on public transport, funded by the City of Kansas City, Missouri.[26]

See also

References
  1. "Having the Right license is just as important as having a License". 28 June 2017.
  2. Bhartiya, Swapnil (25 December 2015). "2015's most exciting Linux devices". CIO magazine. Archived from the original on 26 June 2018. Retrieved 17 March 2017.
  3. Hunckler, Matt (25 July 2017). "5 Growing Artificial Intelligence Startups You Need to Know About". Inc.com. Retrieved 6 October 2017.
  4. Hunckler, Matt (15 May 2017). "This Open-Source AI Voice Assistant Is Challenging Siri and Alexa for Market Superiority". Forbes. Archived from the original on 13 October 2017. Retrieved 6 October 2017.
  5. https://mycroft.ai/blog/why-name-it-mycroft/
  6. Harrington, Rebecca (1 January 2016). "Customize An Open-Source HAL For Your Home". Popular Science. Archived from the original on 27 June 2018. Retrieved 17 March 2017.
  7. Bhartiya, Swapnil (17 January 2016). "Mycroft: Linux's Own AI". Linux.com. Retrieved 19 April 2016.
  8. Mycroft AI (2018-05-24), Mycroft StartEngine Equity Offering, retrieved 2018-07-08
  9. "Alexa can you find me a better assistant? | Techweek". Techweek. 2017-09-11. Archived from the original on 2018-07-09. Retrieved 2018-07-08.
  10. Fein, John (22 February 2016). "Announcing the 2016 Class of the Sprint Accelerator Powered by Techstars!". Techstars. Archived from the original on 30 September 2017. Retrieved 29 September 2017.
  11. Lynley, Matthew (8 February 2017). "Here's the 20th batch of 500 Startups companies". TechCrunch. Archived from the original on 30 September 2017. Retrieved 29 September 2017.
  12. Burch, Bobby (27 February 2017). "Jaguar Land Rover invests in artificial intelligence startup Mycroft". Startland News. Archived from the original on 12 January 2018. Retrieved 29 September 2017.
  13. "Mycroft AI". StartEngine. Retrieved 2018-07-08.
  14. "Precise Wake Word Engine". GitHub. 30 March 2020.
  15. Smith, Katie. "Developing an Open Source Voice Assistant: Interview with Mycroft AI's Steve Penrod". All About Circuits. Retrieved 24 October 2018.
  16. Gold, Jon (7 January 2016). "Raspberry Pi-based home AI project open-sources key components". Network World. Archived from the original on 19 May 2018. Retrieved 17 March 2017.
  17. Stahie, Silviu (7 January 2016). "Mycroft Releases Key AI Component as Open Source". Softpedia News. Archived from the original on 12 June 2018. Retrieved 24 April 2016.
  18. MSV, Janakiram (20 August 2015). "Meet Mycroft, The Open Source Alternative To Amazon Echo". Forbes. Archived from the original on 14 February 2018. Retrieved 17 March 2017.
  19. Stahie, Silviu (14 August 2015). "Mycroft Is an AI for Your Home Powered by Raspberry Pi 2 and Ubuntu Snappy". Softpedia News. Archived from the original on 6 June 2017. Retrieved 17 March 2017.
  20. Crist, Ry (17 August 2015). "Meet Mycroft, an open-source smart-home AI platform". CNET. CBS Interactive. Archived from the original on 21 June 2017. Retrieved 17 March 2017.
  21. "Github: Mycroft Mark I hardware". GitHub. Retrieved 18 March 2018.
  22. Adair, Kris (4 April 2016). "Making a Mycroft & First Shipment". Mycroft blog. Archived from the original on 27 June 2018. Retrieved 18 March 2018.
  23. Montgomery, Joshua (25 January 2018). "Mycroft Mark II: The Open Voice Assistant". Kickstarter. Archived from the original on 19 March 2018. Retrieved 18 March 2018.
  24. "Mycroft AI". StartEngine. Retrieved 2018-07-08.
  25. "Using Precise to Help Refugees - Mycroft Partners with WorkAround". 14 May 2018. Retrieved 24 October 2018.
  26. Bezner, Elyssa. "Collaboration in the air: Cough detection sensors combine Sickweather, Mycroft tech". StartlandNews. Retrieved 24 October 2018.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.