Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fong, Seraphina, Matassoni, Marco, Brutti, Alessio
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
by: Gaido, Marco, et al.
Published: (2024)

The Eloquence team submission for task 1 of MLC-SLM challenge
by: Concina, Lorenzo, et al.
Published: (2025)

Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages
by: Sharma, Swati, et al.
Published: (2026)

Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap
by: Yang, Guanrou, et al.
Published: (2024)

Pretraining Large Brain Language Model for Active BCI: Silent Speech
by: Zhou, Jinzhao, et al.
Published: (2025)

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
by: Song, Zheshu, et al.
Published: (2024)

Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing
by: Peng, An-Ci, et al.
Published: (2026)

A2TTS: TTS for Low Resource Indian Languages
by: Bhadoriya, Ayush Singh, et al.
Published: (2025)

Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models
by: Manakul, Potsawee, et al.
Published: (2024)

TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
by: Yang, Cheng-Yeh, et al.
Published: (2026)

ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
by: Diwan, Anuj, et al.
Published: (2026)

End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data
by: Pothula, Aishwarya, et al.
Published: (2025)

TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
by: Peng, Jing, et al.
Published: (2026)

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions
by: Meng, Lingwei, et al.
Published: (2024)

Can Speech LLMs Think while Listening?
by: Shih, Yi-Jen, et al.
Published: (2025)

Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages
by: Ayrapetyan, Alexan, et al.
Published: (2025)

Closing the Gap Between Text and Speech Understanding in LLMs
by: Cuervo, Santiago, et al.
Published: (2025)

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
by: Fang, Yangui, et al.
Published: (2025)

Phonology-Guided Speech-to-Speech Translation for African Languages
by: Ochieng, Peter, et al.
Published: (2024)

Adaptability of ASR Models on Low-Resource Language: A Comparative Study of Whisper and Wav2Vec-BERT on Bangla
by: Ridoy, Md Sazzadul Islam, et al.
Published: (2025)

Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion
by: Fischbach, Lea, et al.
Published: (2025)

Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
by: Cappellazzo, Umberto, et al.
Published: (2024)

Advancing Speech Summarization in Multi-modal LLMs with Reinforcement Learning
by: Ling, Shaoshi, et al.
Published: (2025)

Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings
by: Attia, Ahmed Adel, et al.
Published: (2024)

Speechless: Speech Instruction Training Without Speech for Low Resource Languages
by: Dao, Alan, et al.
Published: (2025)

Textless NLP -- Zero Resource Challenge with Low Resource Compute
by: Ramadass, Krithiga, et al.
Published: (2024)

Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks
by: Hsu, Ming-Hao, et al.
Published: (2023)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
by: Cao, Di, et al.
Published: (2026)

Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages
by: Pillai, Leena G, et al.
Published: (2024)

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
by: Yang, Sicheng, et al.
Published: (2026)

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

COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning
by: Pan, Jing, et al.
Published: (2023)

MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition
by: Xie, Jiamin, et al.
Published: (2023)

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?
by: Billa, Jayadev
Published: (2026)

SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
by: Hsu, Ming-Hao, et al.
Published: (2024)

Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
by: Wang, Qiongqiong, et al.
Published: (2025)

Bemba Speech Translation: Exploring a Low-Resource African Language
by: Farouq, Muhammad Hazim Al, et al.
Published: (2025)

Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition
by: Piñeiro-Martín, Andrés, et al.
Published: (2024)

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
by: Wang, Qiongqiong, et al.
Published: (2025)

WAXAL: A Large-Scale Multilingual African Language Speech Corpus
by: Diack, Abdoulaye, et al.
Published: (2026)