Pre-training for Speech Translation: CTC Meets Optimal Transport
24. července 2023
Řečníci
Phuong-Hang Le
Sprecher:in · 0 Follower:innen
Hongyu Gong
Sprecher:in · 0 Follower:innen
Changhan Wang
Sprecher:in · 0 Follower:innen
Benjamin Lecouteux
Sprecher:in · 0 Follower:innen
Didier Schwab
Sprecher:in · 0 Follower:innen
O prezentaci
The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed for reducing this gap, but most of them require architectural changes in ST training. In this work, we propose to mitigate this issue at the pre-training stage, requiring no change in the ST model. First, we show that the connectionist temporal classification (CTC) loss can reduce the modality gap by design. We provide a quantitative comparison with the more common cross-entropy loss, showing that pre-training with CTC consistently achieves better final ST accuracy. Nevertheless, CTC is only a partial solution and thus, in our second contribution, we propose a novel pre-training method combining CTC and optimal transport to further reduce this gap. Our method pre-trains a Siamese-like model composed of two encoders, one for acoustic inputs and the other for textual inputs, such that they produce representations that are close to each other in the Wasserstein space. Extensive experiments on the standard CoVoST-2 and MuST-C datasets show that our pre-training method applied to vanilla encoder-decoder Transformer achieves state-of-the-art performance under the no-external data setting, and performs on par with recent strong multi-task learning systems trained with external data. Finally, our method can also be applied on top of these multi-task systems, leading to further improvements for these models.The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed for reducing this gap, but most of them require architectural changes in ST training. In this work, we propose to mitigate this issue at the pre-training stage, requiring no change in the ST model. First, we show that the connectionist temporal classification (CTC) loss can reduce the modality gap by design. We provide a quantitative comparison with the more co…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
Später ansehen
Shiwei Zeng, …
Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
Später ansehen
A Nearly-Optimal Construction for Well-Clustered Graphs
Später ansehen
A Generalization of ViT/MLP-Mixer to Graphs
Später ansehen
Xiaoxin He, …
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
Später ansehen
Jiatai Huang, …