paper-with-me

Papers

AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation

2022-12-17 · Xingshan Zeng, Liangyou Li, Qun Liu

To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text prevents the ST model from efficiently inheriting knowledge from the pre-trained models. In this work, we propose AdaTranS for end-to-end ST. It adapts the speech features with a new shrinking mechanism to mitigate the length mismatch between speech and text features by predicting word boundaries. Experiments on the MUST-C dataset demonstrate that AdaTranS achieves better performance than the other shrinking-based methods, with higher inference speed and lower memory usage. Further experiments also show that AdaTranS can be equipped with additional alignment losses to further improve performance.

📄 PDF Abstract BibTeX arXiv:2212.08911

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translationspeech-recognitionSpeech RecognitionTranslation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer

2021-06-09 · Findings (ACL) 2021 8 · Xingshan Zeng, Liangyou Li, Qun Liu

End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work…

RerankingTranslation

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression

2024-03-20 · Zelin He, Ying Sun, Jingyuan Liu, Runze Li

We consider the transfer learning problem in the high dimensional linear regression setting, where the feature dimension is larger than the sample size. To learn transferable information, which may vary across features o…

Transfer Learning

Adaptive Nonlinear Latent Transformation for Conditional Face Editing

2023-07-15 · ICCV 2023 1 · Zhizhong Huang, Siteng Ma, Junping Zhang, Hongming Shan

Recent works for face editing usually manipulate the latent space of StyleGAN via the linear semantic directions. However, they usually suffer from the entanglement of facial attributes, need to tune the optimal editing …

Disentanglement

M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation

2022-07-03 · Jinming Zhao, Hao Yang, Ehsan Shareghi, Gholamreza Haffari

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due …

DecoderSpeech-to-TextSpeech-to-Text TranslationTranslation

AdaTransform: Adaptive Data Transformation

2019-10-01 · ICCV 2019 10 · Zhiqiang Tang, Xi Peng, Tingfeng Li, Yizhe Zhu 외

Data augmentation is widely used to increase data variance in training deep neural networks. However, previous methods require either comprehensive domain knowledge or high computational cost. Can we learn data transform…

Data Augmentation