中文
相关论文

相关论文: Soft Alignment of Modality Space for End-to-end Sp…

200 篇论文

End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and…

计算与语言 · 计算机科学 2020-10-29 Yuchen Liu , Junnan Zhu , Jiajun Zhang , Chengqing Zong

End-to-End Speech Translation (E2E-ST) is the task of translating source speech directly into target text bypassing the intermediate transcription step. The representation discrepancy between the speech and text modalities has motivated…

计算与语言 · 计算机科学 2025-09-24 Abderrahmane Issam , Yusuf Can Semerci , Jan Scholtes , Gerasimos Spanakis

End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try…

计算与语言 · 计算机科学 2023-05-26 Yan Zhou , Qingkai Fang , Yang Feng

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, we propose…

计算与语言 · 计算机科学 2021-06-10 Xingshan Zeng , Liangyou Li , Qun Liu

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which…

计算与语言 · 计算机科学 2022-10-19 Chen Wang , Yuchen Liu , Boxing Chen , Jiajun Zhang , Wei Luo , Zhongqiang Huang , Chengqing Zong

This paper investigates a novel approach to end-to-end speech translation (ST) based on aligning frozen pre-trained automatic speech recognition (ASR) and machine translation (MT) models via a small connector module (Q-Former, our…

计算与语言 · 计算机科学 2024-11-28 Šimon Sedláček , Santosh Kesiraju , Alexander Polok , Jan Černocký

End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining…

计算与语言 · 计算机科学 2023-10-18 Mutian He , Philip N. Garner

Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing significant challenges due to the complexity of semantic modeling and the scarcity of CS…

计算与语言 · 计算机科学 2026-05-13 Yan Gao , Yazheng Yang , Zhibin Lan , Yidong Chen , Min Zhang , Daimeng Wei , Derek F. Wong , Jinsong Su

Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the…

计算与语言 · 计算机科学 2025-10-14 Nam Luu , Ondřej Bojar

In this paper, we propose a simple yet effective framework for multilingual end-to-end speech translation (ST), in which speech utterances in source languages are directly translated to the desired target languages with a universal…

计算与语言 · 计算机科学 2019-11-01 Hirofumi Inaguma , Kevin Duh , Tatsuya Kawahara , Shinji Watanabe

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…

计算与语言 · 计算机科学 2019-10-09 Mattia Antonino Di Gangi , Matteo Negri , Marco Turchi

The speech-to-singing (STS) voice conversion task aims to generate singing samples corresponding to speech recordings while facing a major challenge: the alignment between the target (singing) pitch contour and the source (speech) content…

音频与语音处理 · 电气工程与系统科学 2023-05-25 Ruiqi Li , Rongjie Huang , Lichao Zhang , Jinglin Liu , Zhou Zhao

Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such as wait-k and…

计算与语言 · 计算机科学 2020-11-05 Xutai Ma , Juan Pino , Philipp Koehn

Pre-training and fine-tuning is a paradigm for alleviating the data scarcity problem in end-to-end speech translation (E2E ST). The commonplace "modality gap" between speech and text data often leads to inconsistent inputs between…

计算与语言 · 计算机科学 2023-06-14 Yuchen Han , Chen Xu , Tong Xiao , Jingbo Zhu

Language-agnostic many-to-one end-to-end speech translation models can convert audio signals from different source languages into text in a target language. These models do not need source language identification, which improves user…

计算与语言 · 计算机科学 2024-06-18 Peidong Wang , Jian Xue , Jinyu Li , Junkun Chen , Aswin Shanmugam Subramanian

In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper, we harness the complementary strengths of speech and text,…

计算与语言 · 计算机科学 2023-05-24 Wenbiao Yin , Zhicheng Liu , Chengqi Zhao , Tao Wang , Jian Tong , Rong Ye

How to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge between ST and MT in which…

计算与语言 · 计算机科学 2023-05-16 Qingkai Fang , Yang Feng

Simultaneous speech translation (SST) aims to provide real-time translation of spoken language, even before the speaker finishes their sentence. Traditionally, SST has been addressed primarily by cascaded systems that decompose the task…

计算与语言 · 计算机科学 2023-10-18 Peter Polák

Speech-to-text translation pertains to the task of converting speech signals in a language to text in another language. It finds its application in various domains, such as hands-free communication, dictation, video lecture transcription,…

计算与语言 · 计算机科学 2024-06-11 Nivedita Sethiya , Chandresh Kumar Maurya

Significant improvements in end-to-end speech translation (ST) have been achieved through the application of multi-task learning. However, the extent to which auxiliary tasks are highly consistent with the ST task, and how much this…

计算与语言 · 计算机科学 2023-11-08 Yuhao Zhang , Chen Xu , Bei Li , Hao Chen , Tong Xiao , Chunliang Zhang , Jingbo Zhu
‹ 上一页 1 2 3 10 下一页 ›