FLEURS

FLEURS is a benchmark used to evaluate speech-to-text translation performance across multiple languages, including the assessment of translation quality in the context of the KUTED dataset for Central Kurdish.

Papers using FLEURS (52)

FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System2026Whispering in Amharic: Fine-tuning Whisper for Low-resource Language2025 · 7 citesTowards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages2025 · 5 citesLanguage-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR2025 · 4 citesBandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation2026Using Songs to Improve Kazakh Automatic Speech Recognition2026Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition2025 · 1 citesSN-WER: Script-Normalized WER for Multi-Script Indic ASR Evaluation2026Benchmarking Speech-to-Speech Translation Models2026A Comparative Study of Pre-trained Speech Encoders and Training Objectives for Large-Scale Indic Spoken Language Identification2026PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation2026Sometin Beta Pass Notin (SBPN): Improving Multilingual ASR for Nigerian Languages via Knowledge Distillation2026English to Central Kurdish Speech Translation: Corpus Creation, Evaluation, and Orthographic Standardization2026Script Collapse in Multilingual ASR: Defining and Measuring Script Fidelity Rate2026VietSuperSpeech: A Large-Scale Vietnamese Conversational Speech Dataset for ASR Fine-Tuning in Chatbot, Customer Support, and Call Center Applications2026Two-Stage Adaptation for Non-Normative Speech Recognition: Revisiting Speaker-Independent Initialization for Personalization2026FLEURS-Kobani: Extending the FLEURS Dataset for Northern Kurdish2026MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages2025POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation2025PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs2025DQLoRA: A Lightweight Domain-Aware Denoising ASR via Adapter-guided Distillation2025Training-Free Voice Conversion with Factorized Optimal Transport2025Improving Language and Modality Transfer in Translation by Character-level Modeling2025On the use of Performer and Agent Attention for Spoken Language Identification2025AfriHuBERT: A self-supervised speech representation model for African languages2024Scaling Speech Technology to 1,000+ Languages2023 · 116 citesImproving Massively Multilingual ASR With Auxiliary CTC Objectives2023 · 26 citesFLEURS: Few-shot Learning Evaluation of Universal Representations of Speech2022 · 15 citesSeamlessM4T: Massively Multilingual & Multimodal Machine Translation2023 · 13 citesMultilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study2024 · 7 citesA Compact End-to-End Model with Local and Global Context for Spoken Language Identification2022 · 4 citesSpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations2022 · 4 citesGigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement2024 · 2 citesCTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation2024 · 1 citesMaestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR2022Label Aware Speech Representation Learning For Language Identification2023Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer2023HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification2023Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges2024GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators2024Africa-Centric Self-Supervised Pre-Training for Multilingual Speech Representation in a Sub-Saharan Context2024ASTRA: Aligning Speech and Text Representations for Asr without Sampling2024Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR2024Investigating Decoder-only Large Language Models for Speech-to-text Translation2024FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks2024ASR Benchmarking: Need for a More Representative Conversational Dataset2024EMMeTT: Efficient Multimodal Machine Translation Training2024Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking2024Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning2024DENOASR: Debiasing ASRs through Selective Denoising2024Whisper Finetuning on Nepali Language2024