Imagen de Portada

Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Issam, Abderrahmane, Semerci, Yusuf Can, Scholtes, Jan, Spanakis, Gerasimos
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment
por: Issam, Abderrahmane, et al.
Publicado: (2025)

A Representation Level Analysis of NMT Model Robustness to Grammatical Errors
por: Issam, Abderrahmane, et al.
Publicado: (2025)

Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters
por: Issam, Abderrahmane, et al.
Publicado: (2024)

Language Models as Artificial Learners: Investigating Crosslinguistic Influence
por: Issam, Abderrahmane, et al.
Publicado: (2026)

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
por: Mąka, Paweł, et al.
Publicado: (2025)

Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models
por: Mąka, Paweł, et al.
Publicado: (2024)

Sequence Shortening for Context-Aware Machine Translation
por: Mąka, Paweł, et al.
Publicado: (2024)

From FusHa to Folk: Exploring Cross-Lingual Transfer in Arabic Language Models
por: Khalak, Abdulmuizz, et al.
Publicado: (2026)

Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch
por: Strazda, Elza, et al.
Publicado: (2025)

Maastricht University at AMIYA: Adapting LLMs for Dialectal Arabic using Fine-tuning and MBR Decoding
por: Alali, Abdulhai, et al.
Publicado: (2026)

Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain
por: Louis, Antoine, et al.
Publicado: (2024)

Traceable by Design: An LLM Pipeline and Dashboard for EU Regulatory Consultation Analysis
por: Bertaglia, Thales, et al.
Publicado: (2026)

Computational Studies in Influencer Marketing: A Systematic Literature Review
por: Gui, Haoyang, et al.
Publicado: (2025)

Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning
por: Thil, Lucas-Andreï, et al.
Publicado: (2024)

Unifying Adversarial Robustness and Training Across Text Scoring Models
por: Tamber, Manveer Singh, et al.
Publicado: (2026)

ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval
por: Louis, Antoine, et al.
Publicado: (2024)

Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples
por: Samadi, Anahita, et al.
Publicado: (2024)

Text-to-Code Generation with Modality-relative Pre-training
por: Christopoulou, Fenia, et al.
Publicado: (2024)

Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets
por: Manafi, Shadi, et al.
Publicado: (2024)

Cross-Lingual Transfer Learning for Speech Translation
por: Ma, Rao, et al.
Publicado: (2024)

How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations
por: Lee, Hyunji, et al.
Publicado: (2024)

MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data
por: Saxena, Vageesh, et al.
Publicado: (2024)

Triple-Encoders: Representations That Fire Together, Wire Together
por: Erker, Justus-Jonas, et al.
Publicado: (2024)

Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss
por: Liu, Meizhu, et al.
Publicado: (2026)

LegalLens Shared Task 2024: Legal Violation Identification in Unstructured Text
por: Hagag, Ben, et al.
Publicado: (2024)

Evaluating LLM-Generated Legal Explanations for Regulatory Compliance in Social Media Influencer Marketing
por: Gui, Haoyang, et al.
Publicado: (2025)

POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
por: Li, Xuanchen, et al.
Publicado: (2025)

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
por: Futami, Hayato, et al.
Publicado: (2025)

CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
por: Du, Yexing, et al.
Publicado: (2025)

Across Platforms and Languages: Dutch Influencers and Legal Disclosures on Instagram, YouTube and TikTok
por: Gui, Haoyang, et al.
Publicado: (2024)

On Adversarial Robustness of Language Models in Transfer Learning
por: Turbal, Bohdan, et al.
Publicado: (2024)

Generation-Step-Aware Framework for Cross-Modal Representation and Control in Multilingual Speech-Text Models
por: Nakai, Toshiki, et al.
Publicado: (2026)

Late Fusion and Multi-Level Fission Amplify Cross-Modal Transfer in Text-Speech LMs
por: Cuervo, Santiago, et al.
Publicado: (2025)

EmoAra: Emotion-Preserving English Speech Transcription and Cross-Lingual Translation with Arabic Text-to-Speech
por: Hassan, Besher, et al.
Publicado: (2026)

Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios
por: Gállego, Gerard I., et al.
Publicado: (2025)

Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking
por: Vendrame, Katia, et al.
Publicado: (2025)

A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation
por: Meyer, Francois, et al.
Publicado: (2024)

Improving Language and Modality Transfer in Translation by Character-level Modeling
por: Tsiamas, Ioannis, et al.
Publicado: (2025)

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
por: Omnilingual SONAR Team, et al.
Publicado: (2026)

TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality
por: Feng, Tiantian, et al.
Publicado: (2024)