WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data

• URL: http://arxiv.org/abs/2605.13846v1
• Date: Wed, 13 May 2026 17:59:52 GMT
• Title: WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
• Abstract summary: This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman into English.<n>We only have 6 hours of annotated audio.<n>We empirically demonstrate that this two-stage design works better than data-hungry unified approaches in extremely low data settings.
• Score: 22.4502082449321
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous language into English. The significant challenge we face is the lack of large-scale training data: in fact, we only have 6 hours of annotated audio. Therefore, while it is common practice to train a single model for transcription and translation using large datasets (like English to French), this practice is no longer viable in the Wardaman to English context. To tackle the low-resource challenge, we design WARDEN to have separate transcription and translation models: WARDEN first turns a Wardaman audio input into phonemic transcription, and then the transcription into English translation. Further, we propose two useful techniques to enhance performance. For transcription, we initialize the Wardaman token from Sundanese, a language that shares similar phonemes with Wardaman, to accelerate fine-tuning of the transcription model. For translation, we compile a Wardaman-English dictionary from expert annotations, and provide this domain-specific knowledge to a large language model (LLM) to reason and decide the final output. We empirically demonstrate that this two-stage design works better than data-hungry unified approaches in extremely low data settings. Using a mere 6 hours of annotated data, WARDEN outperforms larger open-source and proprietary models and establishes a strong baseline. Data and code are available.

Related papers

• Simultaneous Speech-to-Speech Translation Without Aligned Data [52.467808474293605]
  Simultaneous speech translation requires translating source speech into a target language in real-time.<n>We propose Hibiki-Zero, which eliminates the need for word-level alignments entirely.<n>Hibiki-Zero achieves state-of-the-art performance in translation accuracy, latency, voice transfer, and naturalness across five X-to-English tasks.
  arXiv  Detail & Related papers  (2026-02-11T17:41:01Z)
• Deepfake audio as a data augmentation technique for training automatic speech to text transcription models [55.2480439325792]
  We propose a framework that approaches data augmentation based on deepfake audio. A dataset produced by Indians (in English) was selected, ensuring the presence of a single accent.
  arXiv  Detail & Related papers  (2023-09-22T11:33:03Z)
• Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts [12.097786953347828]
  We present an imitation learning approach where a teacher NMT system corrects the errors of an AST student without relying on manual transcripts. We show that the NMT teacher can recover from errors in automatic transcriptions and is able to correct erroneous translations of the AST student.
  arXiv  Detail & Related papers  (2023-07-17T12:14:45Z)
• The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation [53.907805815477126]
  This paper presents the first relatively large-scale Amharic-English parallel sentence dataset. We build bi-directional Amharic-English translation models by fine-tuning the existing Facebook M2M100 pre-trained model. The results show that the normalization of Amharic homophone characters increases the performance of Amharic-English machine translation in both directions.
  arXiv  Detail & Related papers  (2022-10-27T07:18:53Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition [6.224255518500385]
  We show that monolingual data may be more closely matched to one of the languages in the code-switch pair. We propose a semi-supervised approach for code-switched ASR.
  arXiv  Detail & Related papers  (2021-06-14T18:39:18Z)
• "Wikily" Neural Machine Translation Tailored to Cross-Lingual Tasks [20.837515947519524]
  First sentences and titles of linked Wikipedia pages, as well as cross-lingual image captions, are strong signals for a seed parallel data to extract bilingual dictionaries and cross-lingual word embeddings for mining parallel text from Wikipedia. In image captioning, we train a multi-tasking machine translation and image captioning pipeline for Arabic and English from which the Arabic training data is a wikily translation of the English captioning data. Our captioning results in Arabic are slightly better than that of its supervised model.
  arXiv  Detail & Related papers  (2021-04-16T21:49:12Z)
• Textual Supervision for Visually Grounded Spoken Language Understanding [51.93744335044475]
  Visually-grounded models of spoken language understanding extract semantic information directly from speech. This is useful for low-resource languages, where transcriptions can be expensive or impossible to obtain. Recent work showed that these models can be improved if transcriptions are available at training time.
  arXiv  Detail & Related papers  (2020-10-06T15:16:23Z)
• Consecutive Decoding for Speech-to-text Translation [51.155661276936044]
  COnSecutive Transcription and Translation (COSTT) is an integral approach for speech-to-text translation. The key idea is to generate source transcript and target translation text with a single decoder. Our method is verified on three mainstream datasets.
  arXiv  Detail & Related papers  (2020-09-21T10:10:45Z)

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.