Machine translation for spoken and written language

Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion

Cross-Modal Mutual Learning for Cued Speech Recognition

ENHANCING SPEECH-TO-SPEECH TRANSLATION WITH MULTIPLE TTS TARGETS

Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation

A Token-level Contrastive Framework for Sign Language Translation

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation

Efficient Speech Translation with Dynamic Latent Perceivers

Named Entity Detection and Injection for Direct Speech Translation

T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5