BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Kōrero Māori - indigenous language revitalisation powered by mac
 hine learning - Keoni Mahelona &amp\; Peter-Lucas Jones
DTSTART:20181030T120000Z
DTEND:20181030T130000Z
UID:TALK113905@talks.cam.ac.uk
CONTACT:Anton Ragni
DESCRIPTION:Te Reo Irirangi o Te Hiku o Te Ika (Te Hiku Media) is a non-pr
 ofit organisation whose mission is to preserve and promote te reo Māori\,
  the indigenous language of New Zealand. Over the past 30 years we've reco
 rded thousands of hours of the stories of our people\, most of whom were n
 ative speakers. These stories are rich in culture and traditional knowledg
 e around science\, the environment\, and traditional Māori medicine. Toda
 y\, we operate in digital industries creating technology to help document\
 , conserve\, and share the language and knowledge in novel ways. Central t
 o the development of technology and the collection of data is the formalis
 ation of our cultural practices into our Kaitiakitanga License (1). The li
 cense outlines the way that people are able to access data gathered and ac
 knowledges the value of open source technologies but recognises the impact
  of colonisation on indigenous peoples' ability to access those technologi
 es. This discussion will provide insight into the Kōrero Māori (2) proje
 ct and its progress to date in creating speech to text\, text to speech\, 
 and pronunciation tools. We demonstrate how innovation in language revital
 isation succeeds when an indigenous organization leads the corpus collecti
 on and technology development. We collected more than 300 hours of labeled
  corpus in ten days. This enabled the creation of an automatic speech reco
 gnition (ASR) tool for te reo Māori using Mozilla's DeepSpeech (3) projec
 t with a word error rate of 14%. The ASR tool is being used to speed up th
 e transcription of our native speaker archives (4).\n\n(1) https://github.
 com/tehikumedia/corpora#license-kaitiakitanga\n(2) https://koreromaori.com
 \n(3) https://github.com/mozilla/DeepSpeech\n(4) https://koreromaori.io
LOCATION:Department of Engineering - Lecture Room 12
END:VEVENT
END:VCALENDAR
