Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translation

Autor:	Moslem, Yasmin
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	This paper describes our system submission to the International Conference on Spoken Language Translation (IWSLT 2024) for Irish-to-English speech translation. We built end-to-end systems based on Whisper, and employed a number of data augmentation techniques, such as speech back-translation and noise augmentation. We investigate the effect of using synthetic audio data and discuss several methods for enriching signal diversity. Comment: IWSLT 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.17363 Zobrazit plný text záznamu View this record from Arxiv