I am currently a Senior Staff Research Scientist at Meta, working on multimodal LLM on the GenAI Foundation team (the team that makes and herds Llamas).Previously, I was a Research Lead / Senior TLM at TikTok, where I led the Music Machine Learning Research Team to work on generative AI, controllable end-to-end music generation, and large-scale music understanding.Before that, I was a Research Scientist Manager in the Meta AI Speech Team, where I led the effort to push and deploy the state-of-the-art in end-to-end ASR, rare word and entity recognition, contextual biasing, language model fusion, large-scale multilingual ASR, and spoken language understanding.I have co-authored over 40 peer-reviewed papers in speech and language processing, primarily focusing on making end-to-end ASR more customizable, more accurate on long-tail use cases, more on-device friendly, and more language agnostic. I have served as session chair for ICASSP (2021, 2022, 2023) and INTERSPEECH (2022), and am an active reviewer for ICASSP, INTERSPEECH, ASRU, SLT, TASLP, and Speech Communication.Current CV:https://github.com/ducle90/ducle.github.io/blob/main/DucLe_CV.pdfGoogle Scholar:https://scholar.google.com/citations?user=Zorb5T4AAAAJ&hl=en