Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Impact of Pretraining Data Volume Disparity on Zero-Shot Transfer Robustness in the XTREME-R Suite

Domaine:

natural language processing

Type de record:

paper
Créateur:
Ass
Éditeur:
Zenodo
Hôte:avatar
Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, their applicability is still less explored in low-resource settings. This work investigates the use of Speech LLMs for low-resource Automatic Speech Recognition using the SLAM-ASR framework, where a trainable lightweight projector connects a speech encoder and a LLM. Firstly, we assess training data volume requirements to match Whisper-only performance, re-emphasizing the challenges of limited data. Secondly, we show th Research goal: What is the impact of pretraining data volume disparity on the robustness of zero-shot transfer between high-resource and low-resource languages in the XTREME-R suite? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.7/10.

Visit

doi.orgzenodo.org

Tasks

automatic speech recognitionspeech processingtransfer learning

Tags

impactpretrainingdatavolumedisparityrobustnesszero-shottransfer

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Adversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-RIntermediate-Task Difficulty and Zero-Shot Cross-Lingual Transfer Robustness in XTREME-RImpact of Pretraining Data Volume on Zero-Shot Cross-Lingual Code Generation PerformanceMultimodal Pretraining as Intermediate Tasks for Zero-Shot Cross-Lingual Transfer in Low-Resource Languages on XTREME-RImpact of English Intermediate-Task Training on Zero-Shot Robustness for Typologically Distant Languages in XTREME-RIntermediate-task Training Effects on Zero-shot Cross-lingual Robustness in XTREME-R

Adversarial Training Impact on Zero-Shot Cross-Lingual Robustness in XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Intermediate-Task Difficulty and Zero-Shot Cross-Lingual Transfer Robustness in XTREME-R

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Impact of Pretraining Data Volume on Zero-Shot Cross-Lingual Code Generation Performance

Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in l

Multimodal Pretraining as Intermediate Tasks for Zero-Shot Cross-Lingual Transfer in Low-Resource Languages on XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Impact of English Intermediate-Task Training on Zero-Shot Robustness for Typologically Distant Languages in XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Intermediate-task Training Effects on Zero-shot Cross-lingual Robustness in XTREME-R

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni