paper-with-me

홈 › Papers

TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages

2024-02-25 · Minsu Kim, Jee-weon Jung, Hyeongseop Rha, Soumi Maiti, Siddhant Arora, Xuankai Chang, Shinji Watanabe, Yong Man Ro

The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We propose a novel Tri-Modal Translation (TMT) model that translates between arbitrary modalities spanning speech, image, and text. We introduce a novel viewpoint, where we interpret different modalities as different languages, and treat multi-modal translation as a well-established machine translation problem. To this end, we tokenize speech and image data into discrete tokens, which provide a unified interface across modalities and significantly decrease the computational cost. In the proposed TMT, a multi-modal encoder-decoder conducts the core translation, whereas modality-specific processing is conducted only within the tokenization and detokenization stages. We evaluate the proposed TMT on all six modality translation tasks. TMT outperforms single model counterparts consistently, demonstrating that unifying tasks is beneficial not only for practicality but also for performance.

📄 PDF Abstract BibTeX arXiv:2402.16021

Code (1)

ms-dot-k/tmt 공식 구현 pytorch

Tasks

DecoderMachine TranslationTranslation

Similar Papers 제목 키워드 기반

T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation

2022-05-24 · Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, Holger Schwenk

We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare dif…

DecoderMachine Translationtext-to-speechText to Speech+2

Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion

2026-02-25 · Yexing Du, Youcheng Pan, Zekun Wang, Zheng Chu 외 arxiv

Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primarily focuses on image-guided methods, who…

Multimodal Machine Translation

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation

2023-05-24 · Yan Zhou, Qingkai Fang, Yang Feng

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…

Machine TranslationTranslation

Improving speech translation by fusing speech and text

2023-05-23 · Wenbiao Yin, Zhicheng Liu, Chengqi Zhao, Tao Wang 외

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 o…

cross-modal alignmentMachine TranslationTranslation

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