TWB and Kobo Inc develop speech recognition technology to capture voices of speakers of marginalized languages

Cambridge, Mass., USA – September 1, 2020

Kobo and Translators without Borders (TWB) with funding from the Cisco Foundation, will develop automatic speech recognition technology to help humanitarians better collect data from speakers of marginalized languages in low-literacy contexts. The initiative is part of TWB’s ongoing strategy to develop language technology for people with lower literacy and Kobo’s Inc mission to provide accessible yet powerful tools for humanitarian data collection and management.

Through the collaborative initiative, TWB and Kobo will develop speech recognition technology and speech-to-text mechanisms to integrate with data collection and management tool. Humanitarians will be able to use this integrated tool to engage people and conduct assessment on a wide range of topics, including people’s views on coronavirus, their access to food and water, and what languages they speak and understand.

Automated language support will allow people to communicate with humanitarians more accurately, efficiently, and safely. With the COVID-19 pandemic, humanitarians are struggling to engage people living in vulnerable situations as access is reduced and movement is restricted. This tool ensures that the voices of people living through humanitarian crises are heard, even during a pandemic.

“We must listen to the voices of people that have historically been marginalized due to the languages they speak,” says Grace Tang, Gamayun Program Manager at TWB. “This collaboration with Cisco and Kobo is urgently needed and will help ensure voice recognition technology is a key part of communicating with speakers of marginalized languages and with those who have lower literacy levels, especially during COVID-19.”

TWB will first model languages for speech recognition in the Democratic Republic of Congo, like French and Congolese Swahili. In collaboration with local researchers, TWB will gather a wide range of voices for a small collection of basic words. Kobo will then integrate this technology into KoboToolbox, a popular field data collection tool among humanitarians.

“This technology – used responsibly – will ensure that humanitarians process what people are telling them on the ground more effectively” says Patrick Vinck, Kobo Co-Founder. “Feedback from communities is too often ‘lost in translation’ and does not lead to operational changes in humanitarian action.”

This project builds on a successful pilot project funded by the Cisco Foundation, which developed machine translation and open-source language datasets in six additional languages. “The Cisco Foundation is excited to support this scalable, technology-driven initiative that makes sure even the most vulnerable people are heard during the COVID-19 crisis,” says Erin Connor, the Critical Human Needs Portfolio Manager at the Cisco Foundation. “This new collaboration between TWB and Kobo Toolbox unites two technologies that, together, will help humanitarians better understand the needs of people who speak marginalized languages.”

It also represents another step towards addressing the linguistic needs of marginalized language speakers during the COVID-19 pandemic. Since the outbreak was declared a global pandemic in March 2020 by the World Health Organization, TWB has been supporting speakers of marginalized languages, translating over four million words of COVID-19 information and creating a multilingual COVID-19 glossary. TWB has also developed language technology through TICO-19, a consortium of industry and academic partners. TICO-19 makes COVID-19 and crisis-related information accessible in as many languages as possible. This project is part of TWB’s language equality initiative, Gamayun, which uses advanced language technology to increase language equality and improve two-way communication in marginalized languages. The ultimate goal is to enable everyone to give and receive information in the language and format they understand.

It is also an important step towards improving data quality and availability in humanitarian settings. Throughout the pandemic, Kobo Inc has continued to serve humanitarians conducting in-person and remote assessments with its free and open-source tools. Kobo Inc. has supported multi-country assessments of perception towards COVID-19, most notably among healthcare workers, and developed templates for COVID-19 related assessments in partnership with humanitarian agencies. This project is part of Kobo Inc.’s effort to enhance qualitative data collection and analysis in humanitarian action.

About Kobo

Kobo works to ensure that humanitarian action and initiatives promoting peace, human rights and sustainable development are informed by high quality, up-to-date data generated by and with concerned communities using simple, reliable and secure technologies. We host and maintain KoboToolbox, a data collection, management, and visualization platform used globally for humanitarian actions.

For media inquiries, contact Patrick Vinck, patrick.vinck@kobotoolbox.org

About Translators without Borders

Translators without Borders (TWB) envisions a world where knowledge knows no language barriers. The US-based non-profit provides people access to vital knowledge in their language by connecting non-profit organizations with a community of language professionals, building local language solutions, and raising awareness of the power of language. Originally founded in 1993 in France (as Traducteurs sans Frontières), TWB translates millions of words of life-saving and life-changing information a year.

For media inquiries, contact krissy@translatorswithoutborders.org