Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Unsupervised ASR via Cross-Lingual Pseudo-Labeling

Domain:

natural language processing

Record type:

paper
Creator:
LikLugCol
Host:avatar
Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for training. We argue that even if one does not have any labeled audio for a given language, there is $\textit{always}$ labeled data available for other languages. We show that it is possible to use character-level acoustic models (AMs) from other languages to bootstrap an $\textit{unsupervised}$ AM in a new language. Here, "unsupervised" means no labeled audio is available for the $\textit{target}$ language. Our approach is based on two key ingredients: (i) generating pseudo-labels (PLs) of the $\textit{target}$ language using some $\textit{other}$ language AM and (ii) constraining these PLs with a $\textit{target language model}$. Our approach is effective on Common Voice: e.g. transfer of English AM to Swahili achieves 18% WER. It also outperforms character-based wav2vec-U 2.0 by 15% absolute WER on LJSpeech with 800h of labeled German data instead of 60k hours of unlabeled English data.

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

Swahili

Tags

Audio and Speech ProcessingComputation and LanguageMachine LearningSound

Similar

Empowering Low-Resource Language ASR via Large-Scale Pseudo LabelingUnsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo MultilabelPerformance comparison of cross-lingual NER models with multi-source pseudo-labeling versus synthetic data augmentation inMultisensor temporal unsupervised domain adaptation for land cover mapping with spatial pseudo-labeling and adversarial learningZero-Shot Morphological Discovery in Low-Resource Bantu Languages via Cross-Lingual Transfer and Unsupervised ClusteringUnsupervised Cross-lingual Representation Learning at Scale

Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling

In this study, we tackle the challenge of limited labeled data for low-resource languages in ASR, fo

Unsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo Multilabel

Speech Emotion Recognition (SER) in a single language has achieved remarkable results through deep l

Performance comparison of cross-lingual NER models with multi-source pseudo-labeling versus synthetic data augmentation in

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Multisensor temporal unsupervised domain adaptation for land cover mapping with spatial pseudo-labeling and adversarial learning

Source Agritrop Cirad (https://agritrop.cirad.fr/608592/) International audience With

Zero-Shot Morphological Discovery in Low-Resource Bantu Languages via Cross-Lingual Transfer and Unsupervised Clustering

We present a method for discovering morphological features in low-resource Bantu languages by combin

Unsupervised Cross-lingual Representation Learning at Scale

This paper shows that pretraining multilingual language models at scale leads to significant performance gains for a wide range of cross-lingual transfer tasks. We train a Transformer-based masked language model on one hundred languages, using more than two terabyt