Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
Paper
•
2402.12025
•
Published
•
2
Meetween's Research Papers
Research papers published within the MEETWEEN project
-
-
StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
Paper • 2406.06097 • Published • 2 -
SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
Paper • 2406.14177 • Published • 1 -
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
Paper • 2410.01036 • Published • 16 -
What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study
Paper • 2410.00545 • Published • 5 -
How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?
Paper • 2412.18495 • Published • 9 -
How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not
Paper • 2409.17044 • Published • 3 -
NUTSHELL: A Dataset for Abstract Generation from Scientific Talks
Paper • 2502.16942 • Published • 1 -
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
Paper • 2507.19634 • Published • 9 -
Cross-Attention is Half Explanation in Speech-to-Text Models
Paper • 2509.18010 • Published • 5 -
Better Late Than Never: Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation
Paper • 2509.17349 • Published • 2 -
KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025
Paper • 2505.13036 • Published -
How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations
Paper • 2411.17666 • Published -
Early-Exit and Instant Confidence Translation Quality Estimation
Paper • 2502.14429 • Published • 4 -
Are Generative Models Underconfident? An Embarrassingly Simple Quality Estimation Approach
Paper • 2502.11115 • Published -
MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models
Paper • 2411.18152 • Published • 1 -
Cocktail-Party Audio-Visual Speech Recognition
Paper • 2506.02178 • Published -
Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation
Paper • 2405.04327 • Published -
Audio-driven Talking Face Generation with Stabilized Synchronization Loss
Paper • 2307.09368 • Published -
Summarizing Speech: A Comprehensive Survey
Paper • 2504.08024 • Published -
Contrastive Learning for Task-Independent SpeechLLM-Pretraining
Paper • 2412.15712 • Published -
Quality Estimation with k-nearest Neighbors and Automatic Evaluation for Model-specific Quality Estimation
Paper • 2404.18031 • Published -
Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024
Paper • 2406.16777 • Published -
Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach
Paper • 2409.09009 • Published -
COMET-poly: Machine Translation Metric Grounded in Other Candidates
Paper • 2508.18549 • Published -
PIER: A Novel Metric for Evaluating What Matters in Code-Switching
Paper • 2501.09512 • Published -
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages
Paper • 2408.02290 • Published -
Continuously Learning New Words in Automatic Speech Recognition
Paper • 2401.04482 • Published -
Weight Factorization and Centralization for Continual Learning in Speech Recognition
Paper • 2506.16574 • Published -
Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion
Paper • 2506.04013 • Published -
Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement
Paper • 2506.16580 • Published