paper-with-me

Papers

AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation

2025-03-18 · Findings (ACL) 2021 8 · Wuwei Huang, Dexin Wang, Deyi Xiong

In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in speech translation. In this paper, we show the benefits of varying acoustic states according to decoder hidden states and propose an adaptive speech-to-text translation model that is able to dynamically adapt acoustic states in the decoder. We concatenate the acoustic state and target word embedding sequence and feed the concatenated sequence into subsequent blocks in the decoder. In order to model the deep interaction between acoustic states and target hidden states, a speech-text mixed attention sublayer is introduced to replace the conventional cross-attention network. Experiment results on two widely-used datasets show that the proposed method significantly outperforms state-of-the-art neural speech translation models.

📄 PDF Abstract BibTeX arXiv:2503.14185

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderSpeech-to-TextSpeech-to-Text TranslationTranslation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

2025-04-13 · Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng 외

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, res…

Safety Alignment

AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners

2025-05-22 · Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee 외

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often…

Diversity

Continual Speech Learning with Fused Speech Features

2025-06-02 · Guitao Wang, Jinming Zhao, Hao Yang, Guilin Qi 외

Rapid growth in speech data demands adaptive models, as traditional static methods fail to keep pace with dynamic and diverse speech information. We introduce continuous speech learning, a new set-up targeting at bridgin…

Decoder

Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks

2025-03-04 · Paul Suganthan, Fedor Moiseev, Le Yan, Junru Wu 외

Decoder-based transformers, while revolutionizing language modeling and scaling to immense sizes, have not completely overtaken encoder-heavy architectures in natural language processing. Specifically, encoder-only model…

DecoderLanguage ModelingLanguage Modelling

Deformable Stacked Structure for Named Entity Recognition

2018-09-24 · Shuyang Cao, Xipeng Qiu, Xuanjing Huang

Neural architecture for named entity recognition has achieved great success in the field of natural language processing. Currently, the dominating architecture consists of a bi-directional recurrent neural network (RNN) …

Decodernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)