arXiv AI August 5, 2026 By Seraphina Fong, Marco Matassoni, Alessio Brutti

Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages

arXiv:2508. 05149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 22

Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking

arXiv:2609.23825v1 Announce Type: new Abstract: We present a comprehensive benchmark of Federated Learning (FL) for multilingual Automatic Speech Recognition (ASR), evaluating four Speech-LLM archite...

By Jordi Luque, Aleix Sant, Fernando L\'opez

llms fine-tuning multimodal benchmarks safety

arXiv AI

Aug 6

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Aug 7

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

By Yexing Du, Kaiyuan Liu, Youcheng Pan, Bo Yang, Chengpeng Fu, Yu Wang, Ming Liu

llms multimodal benchmarks safety

arXiv AI

Jun 3

Efficient ASR Training with Conversations that Never Happened

arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.

By M\'at\'e Gedeon, P\'eter Mihajlik

llms multimodal benchmarks

Hugging Face Trending Papers

Jun 2

Efficient ASR Training with Conversations that Never Happened

Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose an augmentation pipeline that generates scenario-level dialogues with participant metadata, maps speaker attributes to TTS voice profiles, and assembles synthesized utterances into speaker-aware simulated conversations.

llms multimodal benchmarks

arXiv Computation and Language

Sep 15

Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR

arXiv:2609.15758v1 Announce Type: new Abstract: Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed...

By Thai Thi Thanh Thao Dang, Mengjie Qian, Kate Knill

fine-tuning multimodal

One email a morning, machine-written

Related stories

Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

Efficient ASR Training with Conversations that Never Happened

Efficient ASR Training with Conversations that Never Happened

Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR