Let's Talk, Not Type: An Oral-First Multi-Agent Architecture for Guaraní

• URL: http://arxiv.org/abs/2603.05743v1
• Date: Thu, 05 Mar 2026 23:07:36 GMT
• Title: Let's Talk, Not Type: An Oral-First Multi-Agent Architecture for Guaraní
• Abstract summary: This paper argues that language support in AI remains insufficient unless it aligns with lived oral practices.<n>We propose an alternative to the standard "text-to-speech" pipeline, proposing instead an oral-first multi-agent architecture.
• Score: 0.3181700357675698
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Although artificial intelligence (AI) and Human-Computer Interaction (HCI) systems are often presented as universal solutions, their design remains predominantly text-first, underserving primarily oral languages and indigenous communities. This position paper uses Guaraní, an official and widely spoken language of Paraguay, as a case study to argue that language support in AI remains insufficient unless it aligns with lived oral practices. We propose an alternative to the standard "text-to-speech" pipeline, proposing instead an oral-first multi-agent architecture. By decoupling Guaraní natural language understanding from dedicated agents for conversation state and community-led governance, we demonstrate a technical framework that respects indigenous data sovereignty and diglossia. Our work moves beyond mere recognition to focus on turn-taking, repair, and shared context as the primary locus of interaction. We conclude that for AI to be truly culturally grounded, it must shift from adapting oral languages to text-centric systems to treating spoken conversation as a first-class design requirement, ensuring digital ecosystems empower rather than overlook diverse linguistic practices.

Related papers

• \ extit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language [2.6461502412805062]
  Large Language Models and generative artificial intelligence have been shown to be "unfair" to less-spoken languages and to deepen the digital language divide.<n>This paper argues that these technologies exacerbate epistemologies of language as "monolithic, monolingual, syntactically standardized systems of meaning"<n>We take two different complexes of non-standard linguistic varieties in our respective repertoires--South Tyrolean dialects, which are widely used in informal communication in South Tyrol, Italy, as well as varieties of Kurdish--as starting points to an interdisciplinary exploration of the intersections between GenAI and linguistic variation and standardisation.
  arXiv  Detail & Related papers  (2026-03-30T09:34:41Z)
• Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection [49.27067541740956]
  Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction.<n>Building robust multilingual SER systems remains challenging due to the scarcity of labeled data in languages other than English and Chinese.<n>We propose an approach to enhance SER performance in low SER resource languages by leveraging data from high-resource languages.
  arXiv  Detail & Related papers  (2024-09-17T08:36:45Z)
• Harnessing the Power of Artificial Intelligence to Vitalize Endangered Indigenous Languages: Technologies and Experiences [31.62071644137294]
  We discuss the decreasing diversity of languages in the world and how working with Indigenous languages poses unique ethical challenges for AI and NLP. We report encouraging results in the development of high-quality machine learning translators for Indigenous languages. We present prototypes we have built in projects done in 2023 and 2024 with Indigenous communities in Brazil, aimed at facilitating writing.
  arXiv  Detail & Related papers  (2024-07-17T14:46:37Z)
• Standard Language Ideology in AI-Generated Language [1.2815904071470705]
  Standard language ideology is reflected and reinforced in language generated by large language models (LLMs)<n>We present a faceted taxonomy of open problems that illustrate how standard language ideology manifests in AI-generated language.
  arXiv  Detail & Related papers  (2024-06-13T01:08:40Z)
• Wav2Gloss: Generating Interlinear Glossed Text from Speech [78.64412090339044]
  We propose Wav2Gloss, a task in which four linguistic annotation components are extracted automatically from speech. We provide various baselines to lay the groundwork for future research on Interlinear Glossed Text generation from speech.
  arXiv  Detail & Related papers  (2024-03-19T21:45:29Z)
• What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialects [60.8361859783634]
  We survey speakers of dialects and regional languages related to German. We find that respondents are especially in favour of potential NLP tools that work with dialectal input.
  arXiv  Detail & Related papers  (2024-02-19T09:15:28Z)
• Towards Bridging the Digital Language Divide [4.234367850767171]
  multilingual language processing systems often exhibit a hardwired, yet usually involuntary and hidden representational preference towards certain languages. We show that biased technology is often the result of research and development methodologies that do not do justice to the complexity of the languages being represented. We present a new initiative that aims at reducing linguistic bias through both technological design and methodology.
  arXiv  Detail & Related papers  (2023-07-25T10:53:20Z)
• Including Signed Languages in Natural Language Processing [48.62744923724317]
  Signed languages are the primary means of communication for many deaf and hard of hearing individuals. This position paper calls on the NLP community to include signed languages as a research area with high social and scientific impact.
  arXiv  Detail & Related papers  (2021-05-11T17:37:55Z)
• Crossing the Conversational Chasm: A Primer on Multilingual Task-Oriented Dialogue Systems [51.328224222640614]
  Current state-of-the-art ToD models based on large pretrained neural language models are data hungry. Data acquisition for ToD use cases is expensive and tedious.
  arXiv  Detail & Related papers  (2021-04-17T15:19:56Z)
• ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Games [0.30458514384586394]
  Natural languages are powerful tools wielded by human beings to communicate information and co-operate towards common goals. computational linguists have been researching the emergence of in artificial languages induced by language games. The AI community has started to investigate language emergence and grounding working towards better human-machine interfaces.
  arXiv  Detail & Related papers  (2020-12-17T10:22:15Z)
• Experience Grounds Language [185.73483760454454]
  Language understanding research is held back by a failure to relate language to the physical world it describes and to the social interactions it facilitates. Despite the incredible effectiveness of language processing models to tackle tasks after being trained on text alone, successful linguistic communication relies on a shared experience of the world.
  arXiv  Detail & Related papers  (2020-04-21T16:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.