This paper reports NYA’s submissions to the IWSLT 2025 Offline Speech Translation (ST) task. The task includes three translation directions: English to Chinese, German, and Arabic. In detail, we adopt a cascaded speech translation architecture comprising automatic speech recognition (ASR) and machine translation (MT) components to participate in the unconstrained training track. For the ASR model, we use the Whisper medium model. For the neural machine translation (NMT) model, the wider and deeper Transformer is adopted as the backbone model. Building upon last year’s work, we implement multiple techniques and strategies such as data augmentation, domain adaptation, and model ensemble to improve the translation quality of the NMT model. In addition, we adopt X-ALMA as the foundational LLM-based MT model, with domain-specific supervised fine-tuning applied to train and optimize our LLM-based MT model. Finally, by employing COMET-based Minimum Bayes Risk decoding to integrate and select translation candidates from both NMT and LLM-based MT systems, the translation quality of our ST system is significantly improved, and competitive results are obtained on the evaluation set.

This paper reports the NYA’s submissions to IWSLT 2024 Offline Speech Translation (ST) task on the sub-tasks including English to Chinese, Japanese, and German. In detail, we participate in the unconstrained training track using the cascaded ST structure. For the automatic speech recognition (ASR) model, we use the Whisper large-v3 model. For the neural machine translation (NMT) model, the wider and deeper Transformer is adapted as the backbone model. Furthermore, we use data augmentation technologies to augment training data and data filtering strategies to improve the quality of training data. In addition, we explore many MT technologies such as Back Translation, Forward Translation, R-Drop, and Domain Adaptation.