Self-Supervised Representations Improve End-to-End Speech Translation
원문 초록
End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In this work, we explore whether self-supervised pre-trained speech representations can benefit the speech translation task in both high- and low-resource settings, whether they can transfer well to other languages, and whether they can be effectively combined with other common methods that help improve low-resource end-to-end speech translation such as using a pre-trained high-resource speech recognition system. We demonstrate that self-supervised pre-trained features can consistently improve the translation performance, and cross-lingual transfer allows to extend to a variety of languages without or with little tuning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios
TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS
End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation
Improving Language and Modality Transfer in Translation by Character-level Modeling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.