Cover Image

KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhaolin, Liu, Yining, Liu, Danni, Nguyen, Tuan Nam, Ugan, Enes Yavuz, Dinh, Tu Anh, Mullov, Carlos, Waibel, Alexander, Niehues, Jan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024
by: Koneru, Sai, et al.
Published: (2024)

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025
by: Koneru, Sai, et al.
Published: (2025)

End-to-End Evaluation for Low-Latency Simultaneous Speech Translation
by: Huber, Christian, et al.
Published: (2023)

Adapting Language Balance in Code-Switching Speech
by: Ugan, Enes Yavuz, et al.
Published: (2025)

BOOM: Beyond Only One Modality KIT's Multimodal Multilingual Lecture Companion
by: Koneru, Sai, et al.
Published: (2025)

Weight Factorization and Centralization for Continual Learning in Speech Recognition
by: Ugan, Enes Yavuz, et al.
Published: (2025)

Bayesian Low-Rank Factorization for Robust Model Adaptation
by: Ugan, Enes Yavuz, et al.
Published: (2025)

PIER: A Novel Metric for Evaluating What Matters in Code-Switching
by: Ugan, Enes Yavuz, et al.
Published: (2025)

CMU's IWSLT 2025 Simultaneous Speech Translation System
by: Ouyang, Siqi, et al.
Published: (2025)

MUSCAT: MUltilingual, SCientific ConversATion Benchmark
by: Sinhamahapatra, Supriti, et al.
Published: (2026)

Conditions for Catastrophic Forgetting in Multilingual Translation
by: Liu, Danni, et al.
Published: (2025)

Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems
by: Zink, Oswald, et al.
Published: (2024)

Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach
by: Li, Siqi, et al.
Published: (2024)

Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages
by: Mullov, Carlos, et al.
Published: (2024)

How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?
by: Liu, Danni, et al.
Published: (2023)

GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task
by: Meng, Chutong, et al.
Published: (2025)

CMU's IWSLT 2024 Simultaneous Speech Translation System
by: Xu, Xi, et al.
Published: (2024)

NAIST Simultaneous Speech Translation System for IWSLT 2024
by: Ko, Yuka, et al.
Published: (2024)

Titanic Calling: Low Bandwidth Video Conference from the Titanic Wreck
by: Eyiokur, Fevziye Irem, et al.
Published: (2024)

Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability
by: Dinh, Tu Anh, et al.
Published: (2025)

Sigmoid Head for Quality Estimation under Language Ambiguity
by: Dinh, Tu Anh, et al.
Published: (2026)

BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
by: Raffel, Matthew, et al.
Published: (2025)

Multimodal In-context Learning for ASR of Low-resource Languages
by: Li, Zhaolin, et al.
Published: (2026)

In-context Language Learning for Endangered Languages in Speech Recognition
by: Li, Zhaolin, et al.
Published: (2025)

Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
by: Sperber, Matthias, et al.
Published: (2024)

SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading
by: Dinh, Tu Anh, et al.
Published: (2024)

MLLP-VRAIN UPV system for the IWSLT 2025 Simultaneous Speech Translation Translation task
by: Iranzo-Sánchez, Jorge, et al.
Published: (2025)

Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025
by: Macháček, Dominik, et al.
Published: (2025)

Quality Estimation with $k$-nearest Neighbors and Automatic Evaluation for Model-specific Quality Estimation
by: Dinh, Tu Anh, et al.
Published: (2024)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
by: Liu, Danni, et al.
Published: (2025)

Speech Editing -- a Summary
by: Kässmann, Tobias, et al.
Published: (2024)

HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track
by: Wei, Xuchen, et al.
Published: (2025)

Knockout LLM Assessment: Using Large Language Models for Evaluations through Iterative Pairwise Comparisons
by: Sandan, Isik Baran, et al.
Published: (2025)

From Slides to Chatbots: Enhancing Large Language Models with University Course Materials
by: Dinh, Tu Anh, et al.
Published: (2025)

SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
by: Papi, Sara, et al.
Published: (2024)

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

COMET-poly: Machine Translation Metric Grounded in Other Candidates
by: Züfle, Maike, et al.
Published: (2025)

Language-Independent Representations Improve Zero-Shot Summarization
by: Solovyev, Vladimir, et al.
Published: (2024)

Augmenting Automatic Speech Recognition Models with Disfluency Detection
by: Amann, Robin, et al.
Published: (2024)

Improving Pronunciation and Accent Conversion through Knowledge Distillation And Synthetic Ground-Truth from Native TTS
by: Nguyen, Tuan Nam, et al.
Published: (2024)