Zhihang Xie

PhD Student

    Short bio

    Zhihang Xie is a PhD student at the University of Trento and Fondazione Bruno Kessler.

    He holds a Master's degree in Artificial Intelligence from the University of Edinburgh, specializing in Speech Technologies.

    Research topics

    SpeechLLMs, Long-form Speech Processing


    • Speech Recognition

    • Speech Translation

    • Spoken Question Answering

    • Speech Summarization

    • Audio Chaptering

    MT Group at FBK Follow

    #MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

    Avatar
    Avatar MT Group at FBK @fbk_mt ·
    13 May

    How does the granularity of speech-text pairs impact SpeechLLM performance, and what is the optimal way to interleave tokens? Furthermore, what are the best practices for generating synthetic data to boost training?🧐

    Reply on Twitter 2054503147721097286 Retweet on Twitter 2054503147721097286 Like on Twitter 2054503147721097286 3 Twitter 2054503147721097286
    Retweet on Twitter MT Group at FBK Retweeted
    Avatar Meetween @meetweeneu ·
    26 Mar

    🎙️ Our paper on connecting Speech Foundation Models with LLMs is featured in the SpeechLMM Training Journal on Weights & Biases.

    Read it 👉 https://bit.ly/4svG7ll

    SpeechLMM 2.0 coming this summer. 👀

    #Meetween #SpeechLMM #AI #NLP

    Reply on Twitter 2037102183120879826 Retweet on Twitter 2037102183120879826 1 Like on Twitter 2037102183120879826 3 Twitter 2037102183120879826
    Retweet on Twitter MT Group at FBK Retweeted
    Avatar Meetween @meetweeneu ·
    1 Apr

    Meetween is part of the organising committee of #IWSLT2026 — the premier conference on spoken language translation. The Shared Task Evaluation Period is open. Working on #speechtranslation, instruction following, or #modelcompression?
    Get involved now! 🔗 http://iwslt.org/2026

    Reply on Twitter 2039350814884422112 Retweet on Twitter 2039350814884422112 3 Like on Twitter 2039350814884422112 3 Twitter 2039350814884422112
    Load More