Yi Su (苏毅)

prof_pic.jpg

1 Apple Park Way

Cupertino, CA 95014

I am a seasoned research engineer who possesses a unique combination of skill sets: machine learning research and software engineering.

With a solid education of PhD in speech and language processing and 10+ years of experience on research and development in an industrial setting, I have shipped numerous machine learning features for Apple Siri, Ant Group Intelligent Assistant (“支付宝智能助理”), Ant Group Intelligent Financial Assistant (“支小宝”), Nuance Dragon NaturallySpeaking, Nuance PowerScribe 360 and Nuance Nina Virtual Assistant.

I have also built many internal software and services that are still in use today, including a large-scale n-gram language model trainer, a low-code chatbot development platform and an offline model evaluation framework.

In general, I am interested in statistical modeling of human intelligence as exemplified in the use of language and speech.

news

Mar 13, 2024 Rebuilt my personal website with al-folio and it looks great!
Feb 16, 2024 Check out our ICASSP ‘24 paper!
Jun 09, 2023 Check out my pet project LLaMA Server!
Oct 01, 2022 Check out our JMLR paper and code!

selected publications

  1. ICASSP
    Leveraging large language models for exploiting ASR uncertainty
    Pranay Dighe , Yi Su, Shangshang Zheng , and 4 more authors
    In IEEE International Conference on Acoustics, Speech and Signal Processing , 2024
    PDF Poster
  2. JMLR
    Tianshou: A highly modularized deep reinforcement learning library
    Jiayi Weng , Huayu Chen , Dong Yan , and 6 more authors
    Journal of Machine Learning Research, 2022
    PDF Code