paper-with-me

Papers

AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation

2023-05-19 · Sara Papi, Marco Turchi, Matteo Negri

Attention is the core mechanism of today's most used architectures for natural language processing and has been analyzed from many perspectives, including its effectiveness for machine translation-related tasks. Among these studies, attention resulted to be a useful source of information to get insights about word alignment also when the input text is substituted with audio segments, as in the case of the speech translation (ST) task. In this paper, we propose AlignAtt, a novel policy for simultaneous ST (SimulST) that exploits the attention information to generate source-target alignments that guide the model during inference. Through experiments on the 8 language pairs of MuST-C v1.0, we show that AlignAtt outperforms previous state-of-the-art SimulST policies applied to offline-trained models with gains in terms of BLEU of 2 points and latency reductions ranging from 0.5s to 0.8s across the 8 languages.

📄 PDF Abstract BibTeX arXiv:2305.11408

Code (2)

hlt-mt/fbk-fairseq 공식 구현 pytorch
ahclab/naist-simulst jax

Tasks

Machine TranslationTranslationWord Alignment

Similar Papers 제목 키워드 기반

AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task

2026-06-02 · Quentin Fuxa, Dominik Macháček arxiv

We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronous cascade: Qwen3-ASR with forced alignment produces an incrementally u…

SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation

2024-06-20 · Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli

This paper describes the FBK's participation in the Simultaneous Translation Evaluation Campaign at IWSLT 2024. For this year's submission in the speech-to-text translation (ST) sub-track, we propose SimulSeamless, which…

Speech-to-TextSpeech-to-Text TranslationTranslation

NAIST Simultaneous Speech Translation System for IWSLT 2024

2024-06-30 · Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano 외

This paper describes NAIST's submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-{German, Japanese, Chinese} speech-to-text translation and English-to-Japanese speech-to-speech translat…

Speech-to-Speech TranslationSpeech-to-TextSpeech-to-Text Translationtext-to-speech+2

Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation

2022-03-16 · ACL 2022 5 · Tsz Kin Lam, Shigehiko Schamoni, Stefan Riezler

End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language. Such data are notoriously scarce, making synthetic data augmentation by back-tr…

Data AugmentationKnowledge DistillationTranslation

A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026

2026-06-02 · Aziz Sharipov Ortega, Dominik Macháček arxiv

We implement simultaneous translation capability with the offline direct speech-to-text translation model Canary, using the state-of-the-art policy AlignAtt, and submit it to IWSLT 2026 Simultaneous Speech Translation Sh…

Speech-to-Text Translation