Understanding and Bridging the Modality Gap for Speech Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve end-to-end speech translation (ST) use multitask learning, but there is always a modality gap between ST and MT due to the differences between speech and text. |
| Approach: | They propose a method to bridge the modality gap between ST and MT by leveraging (text) machine translation data. |
| Outcome: | The proposed method bridges the modality gap and achieves significant improvements over baseline in all eight directions. |
Similar Papers
Modality Adaption or Regularization? A Case Study on End-to-End Speech Translation (2023.acl-short)
Copied to clipboard
| Challenge: | End-to-end speech translation models have limited training data and are often inefficient due to the inconsistency of length and representation between speech and text. |
| Approach: | They find that the "modality gap" between speech and text data is not a major problem in E2E ST . they decouple the encoder to speech encoder and text encoder, and they find that there is a 'capacity gap' |
| Outcome: | The proposed model achieves 29.0 for en-de and 40.3 for fr on the MuST-C dataset. |
Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | LSLMs have impressive conversational generation abilities, but consistently fall short of traditional pipeline systems on semantic understanding benchmarks. |
| Approach: | They propose to analyze the performance gap between speech and text inputs through a systematic experiment . they find that representation similarity is strongly correlated with the modality gap . |
| Outcome: | The proposed models improve the accuracy of speech inputs and their semantic understanding benchmarks. |
Consistency is Key: On Data-Efficient Modality Transfer in Speech Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end approaches to speech translation suffer from data scarcity compared to machine translation (MT). |
| Approach: | They propose a method which combines knowledge distillation and consistency learning to break the dilemma of learning-forgetting. |
| Outcome: | The proposed method outperforms the previous methods on a MuST-C dataset even without additional data. |
Pushing the Limits of Zero-shot End-to-End Speech Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to end-to-end Speech Translation (ST) systems require limited data, which can cause data scarcity and performance degradation. |
| Approach: | They propose a method for zero-shot ST that bridges the modality gap without any paired ST data. |
| Outcome: | The proposed method bridges the modality gap without any paired ST data on a speech encoder and on MT models. |
Low-resource Neural Machine Translation with Cross-modal Alignment (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural machine translation techniques rely on large monolingual corpus, which is costly for some low-resource languages. |
| Approach: | They propose a cross-modal contrastive learning method to learn a shared space for all languages by additional visual modality. |
| Outcome: | The proposed method can learn cross-modal and cross-lingual alignment with small amount of image-text pairs and achieves significant improvements over the text-only baseline. |
Rethinking and Improving Multi-task Learning for End-to-end Speech Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | auxiliary tasks are highly consistent with end-to-end speech translation (ST) but their effectiveness has not been thoroughly studied. |
| Approach: | They propose an improved multi-task learning approach for the ST task that bridges the modal gap by mitigating the difference in length and representation. |
| Outcome: | The proposed approach achieves state-of-the-art on the MuST-C dataset with 20.8% of training time required by the current SOTA method. |
Cross-modal Contrastive Learning for Speech Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches for speech translation focus on using additional data from MT and automatic speech recognition (ASR). |
| Approach: | They propose a cross-modal contrastive learning method for end-to-end speech-totext translation. |
| Outcome: | The proposed method outperforms existing methods on a popular benchmark MuST-C. |
PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Image translation is a task that translates an image containing text in the source language to the target language. |
| Approach: | They propose an end-to-end image translation framework that bridges the modality gap between visual inputs and textual inputs/outputs of machine translation (MT). |
| Outcome: | The proposed framework outperforms existing models on a large-scale image translation corpus . it significantly outperformed both cascaded and strong models on the e-commerce domain . |
Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to train cross-lingual pre-trained language models have shown great success in cross-linguistic sequence labeling tasks. |
| Approach: | They propose a cross-lingual language informative span masking task to eliminate the objective gap between pre-training and fine-tuning stages. |
| Outcome: | The proposed method surpasses the state-of-the-art methods on multiple benchmarks even with limited pre-training data. |
Towards Zero-shot Learning for End-to-end Cross-modal Translation Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end zero-shot speech translation model is based on a zero-shot approach, but it is less competitive because of the limited amount of data available for multiple modalities. |
| Approach: | They propose an end-to-end zero-shot speech translation model that connects two pre-trained uni-modality modules via word rotator’s distance. |
| Outcome: | The proposed model performs better than or as well as those of the CTC-based models and can be trained in an end-to-end style to avoid error propagation. |