all AI news
MSLM-S2ST: A Multitask Speech Language Model for Textless Speech-to-Speech Translation with Speaker Style Preservation
March 20, 2024, 4:48 a.m. | Yifan Peng, Ilia Kulikov, Yilin Yang, Sravya Popuri, Hui Lu, Changhan Wang, Hongyu Gong
cs.CL updates on arXiv.org arxiv.org
Abstract: There have been emerging research interest and advances in speech-to-speech translation (S2ST), translating utterances from one language to another. This work proposes Multitask Speech Language Model (MSLM), which is a decoder-only speech language model trained in a multitask setting. Without reliance on text training data, our model is able to support multilingual S2ST with speaker style preserved.
abstract advances arxiv cs.cl cs.sd decoder eess.as language language model preservation reliance research s2st speaker speech speech-to-speech translation style translation type work
More from arxiv.org / cs.CL updates on arXiv.org
Benchmarking LLMs via Uncertainty Quantification
1 day, 12 hours ago |
arxiv.org
CARE: Extracting Experimental Findings From Clinical Literature
1 day, 12 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Global Data Architect, AVP - State Street Global Advisors
@ State Street | Boston, Massachusetts
Data Engineer
@ NTT DATA | Pune, MH, IN