Indigenous Voices in Speech Sciences and Technology

A session exploring the roles of speech sciences and technology in Indigenous cultural vitality and self-determination.

🗓️ When: Tue 29 September 2026, 2pm-4pm

📍 Where: International Convention Centre (ICC) on Gadigal Country in Sydney, Australia

Register at https://interspeech2026.org/en-AU

Overview

The languages spoken by First Nations people in Australia are as diverse as the landscapes of this continent. Primarily oral in nature, these languages are deeply connected to Aboriginal and Torres Strait Islander identities and cultures. However, English-speaking settler colonisation has had negative consequences for the health of these languages, and they tend to be overlooked in speech technology research.
This special session is dedicated to exploring the question: What are roles of speech science and technology projects in advancing Indigenous cultural vitality and self-determination? These topics are under-represented by regular conference sessions, due both to the scarcity of Indigenous speech datasets, as well as the under-representation of Indigenous researchers in speech science and technology research.
This session is designed with a Birds of a Feather structure in mind, to encourage conversation, collaboration, and the sharing of ideas across disciplines, communities, and regions. Rather than a series of traditional presentations, this format creates space for discussion, networking, and the development of new collaborations around shared interests and challenges.
We recognise that Interspeech 2026 will take place on Gadigal Country, in the 5th year of the UN International Decade of Indigenous Languages. This special session, Indigenous Voices in Speech Science and Technology, acknowledges the value of Country, language and culture to Indigenous peoples in Australia. Aboriginal and Torres Strait Islander peoples care for their Country using language which embeds deep traditional knowledges. Stories, ceremony and language are all deeply connected to place.

Accepted papers

  • Pashto Common Voice: Building the First Open Speech Corpus for a 60-Million-Speaker Low-Resource Language

    Hanif Rahman (Pashto DAO)*; Shafeeq ur Rehman (Pashto DAO)

  • Indigenising Speech Technology: Building a TTS Model for te Reo Māori

    Gianna Leoni (Te Reo Irirangi o Te Hiku o te Ika (Te Hiku Media))*; Peter-Lucas Jones (Te Reo Irirangi o Te Hiku o te Ika (Te Hiku Media)); TĹŤreiti Keith (Te Reo Irirangi o Te Hiku o te Ika (Te Hiku Media)); Suzanne Duncan (Te Reo Irirangi o Te Hiku o te Ika (Te Hiku Media))

  • ‘I have to talk proper white ways’: Australian Aboriginal English Speakers’ Experiences with Voice Technologies

    Celeste Rodriguez Louro (University of Western Australia); Glenys Collard (University of Western Australia); Hope Narrier (University of Western Australia); Katrina Cox (University of Western Australia); Lily Hayward (University of Western Australia); Daniel Colbung (University of Western Australia); Ben Hutchinson (Google)*

  • Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR

    Pravina Mylvaganam (The University of New South Wales)*; Eliathamby Ambikairajah (The University of New South Wales); Ting Dang (The University of Melbourne); Vidhyasaharan Sethu (The University of New South Wales); Tuende Szalay (The University of Sydney)

  • From Academic Tool to Community Infrastructure: A Call for Indigenous Partnership in Speech Data Governance

    Kaveri Sheth (Language Acquisition Across Cultures)*; Sebastien Christian (MSHP)

  • Two-stage semi-supervised learning with pseudo-labels: A case study on Northern SĂĄmi ASR

    Priyanshi Pal (Aalto University)*; Yaroslav Getman (Aalto University); Kristiina Ojala (Aalto University); TamĂĄs GrĂłsz (Walton Institute); Mikko Kurimo (Aalto University)

  • Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition

    Kesego Mokgosi (Technological University Dublin)*; Vukosi Marivate (University of Pretoria); Sitwala Mundia (University of Pretoria); Tsholofelo Mogale (University of Pretoria); Thapelo Sindane (University of Pretoria); Unarine Netshifhefhe (University of Pretoria)

Calls for Poster Proposals

The session is designed with a Birds of a Feather structure in mind. To encourage connection and dicsussion, we invite and encourage proposals to present posters on topics related to technology, Indigenous speech communities, and their language varieties. For example, these posters may feature 'late-breaking work' that was not completed by the main conference deadline, or work that has already been presented elsewhere. Posters will be reviews for relevance to the session's themes, which include:
  • Linguistic and sociolinguistic properties of Indigenous languages that present challenges and opportunities for speech science and technology projects;
  • Opportunities for speech technologies to assist in teaching, learning, revitalisation, and re-awakening of Indigenous languages or knowledges;
  • Speech data collection and governance frameworks which respect Indigenous expertise and Indigenous Cultural and Intellectual Property;
  • Technology project partnerships which centre Indigenous communities, and which advance self-determination and building of capabilities;
  • Technology projects which facilitate two-way learning between Indigenous and non-Indigenous communities;
  • Technologies to support post-contact Indigenous language varieties such as Kriol, Light Warlpiri or Aboriginal English.

Poster proposals must be emailed to indigenousvoicesinterspeech@gmail.com any time up to and including Sep 15. Proposals will be reviewed for relevance to the themes listed above, and we will send a notification one week after you submit.
Accepted posters will be given time and space during the special session to present their poster.
Accepted posters will not be published in the conference proceedings, and will not be considered "archival". Posters may submitted even if the work has previously been presented at other venues.

Additionally, we welcome proposals for other forms of participation and contribution to the session. Please email the organisers at indigenousvoicesinterspeech@gmail.com.

Important dates:

  • Sep 15, 2026: Last possible date for submitting poster proposals
  • Sep 29, 2026: Special session takes place

Protocol for the special session

Everybody is welcome in this discussion space. In order to receive the gift of knowledge, participants must be listening actively and intently, without focusing on their response. They will have their chance to contribute in time.

Organisers

Image of Cat Kutay

Cat Kutay

Charles Darwin University

Dr Cat Kutay is descended from seafarers of Yugambeh and Celtic origin. She is a Lecturer in the Faculty of Science and Technology at Charles Darwin University. Dr Kutay works with Aboriginal communities for both-way learning in engineering and IT projects, as a way for Aboriginal culture and knowledges to be acknowledged and integrated into Australian engineering approaches. Her research is in Indigenous knowledge management, Augmented Intelligence (AI) to support Language Learning, Data Sovereignty, and storytelling in gaming.

Image of Janet Wiles

Janet Wiles

University of Queensland

Professor Janet Wiles has 30 years’ experience in research and teaching in machine learning, artificial intelligence, speech and language technologies, and social robotics, leading teams that span engineering, humanities, social sciences and neuroscience. She has developed a cross disciplinary course ”Voyages in Language Technologies” that introduced computing students to the diversity of Indigenous and non-Indigenous languages, and state-of-the-art tools for deep learning and other analysis techniques for working with language data.

Image of Celeste Rodriguez Louro

Celeste Rodriguez Louro

University of Western Australia

Associate Professor Celeste Rodríguez Louro is Director of the Language Lab and Linguistics Discipline Chair at The University of Western Australia. She is Deputy Chair of UWA’s Generative AI Think Tank. Celeste’s work spans language change, decolonisation, and inclusive AI technologies, with funding through the Australian Research Council and industry partnerships including Google and the Heart Foundation, working closely with Nyungar scholar Dr Glenys Collard. Assoc Prof Rodríguez Louro has a strong public presence through award-winning teaching, research, and outreach. Her current book project, co-authored with Dr Collard, is under contract with Cambridge University Press.

Image of Ben Hutchinson

Ben Hutchinson

Google Research

Dr Ben Hutchinson is a senior researcher in Trustworthy and Responsible AI, in Google Research's Human-Centered AI research group. His research includes collaborating across disciplines to inform the ethical development of AI, with a focus on making language technologies and their development more inclusive. Dr Hutchinson is a lead investigator on the project Aboriginal English Voices, and co-led the workshop Envisioning Aboriginal and Torres Strait Islander AI Futures with Butchulla scholar Dr Rose Barrowcliffe.

Image of Daan van Esch

Daan van Esch

Google DeepMind

Daan van Esch is a Senior Technical Program Manager with the Google Speech team, working on internationalisation for speech and language technology at Google, harnessing machine learning and scalable infrastructure to bring support for new languages to products. Daan was also an advisory board member of the Australian Research Council-funded Centre of Excellence for the Dynamics of Language, advising on efforts to bring speech and language technologies to endangered languages in Australia and beyond.