Understanding and Bridging the Modality Gap for Speech Translation
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 additional MT data can help to learn source-to-target mapping. However, due to the differences between speech and text, there is always a gap between ST and MT. In this paper, we first aim to understand this modality gap from the target-side representation differences, and link the modality gap to another well-known problem in neural machine translation: exposure bias. We find that the modality gap is relatively small during training except for some difficult cases, but keeps increasing during inference due to the cascading effect. To address these problems, we propose the Cross-modal Regularization with Scheduled Sampling (Cress) method. Specifically, we regularize the output predictions of ST and MT, whose target-side contexts are derived by sampling between ground truth words and self-generated words with a varying probability. Furthermore, we introduce token-level adaptive training which assigns different training weights to target tokens to handle difficult cases with large modality gaps. Experiments and analysis show that our approach effectively bridges the modality gap, and achieves promising results in all eight directions of the MuST-C dataset.
Code (1)
Tasks
Machine TranslationMulti-Task LearningTranslationSimilar Papers 제목 키워드 기반
Bridging the Modality Gap for Speech-to-Text Translation
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 acousti…
DecoderSpeech-to-TextSpeech-to-Text TranslationTranslationDTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment
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 modaliti…
Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition
In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST)…
speech-recognitionSpeech RecognitionTranslationSparQLe: Speech Queries to Text Translation Through LLMs
With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal processing and speech understanding. This study…
Speech-to-TextSpeech-to-Text TranslationTranslationBalancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
Recent efforts have extended textual LLMs to the speech domain. Yet, a key challenge remains, which is balancing speech understanding and generation while avoiding catastrophic forgetting when integrating acoustically ri…
Automatic Speech RecognitionLanguage ModelingLanguage Modellingspeech-recognition+8