AI People Wiki

Builders & open source

Ju-Chieh Chou

Ph.D. student, advised by Karen Livescu, Toyota Technological Institute at Chicago

  • Ph.D. student, advised by Karen Livescu, Toyota Technological Institute at Chicago14

Ju-Chieh Chou is a final-year PhD student at the Toyota Technological Institute at Chicago (TTIC), advised by Karen Livescu, working on speech and language processing with a focus on learning from multimodal data and generative modeling for speech. Chou's CV lists research internships at Meta AI in 2022, Microsoft in 2024, and Meta in 2025, and earlier at Mila, where Chou developed end-to-end speech recognition recipes within SpeechBrain. During the 2022 Meta AI internship, Chou proposed a joint interleaved language model for discrete speech units and text, published as Toward Joint Language Modeling for Speech Units and Text.1234

At a glance

Current role
Ph.D. student, advised by Karen Livescu
Sector
University
Work listed
2
Honors
2
Sources cited
4
Profile reviewed

Research

Before TTIC, Chou worked on unsupervised voice conversion as a research assistant and master's student at National Taiwan University with Hung-yi Lee and Lin-shan Lee, including Interspeech papers in 2018 and 2019 on separating speaker and content representations. In 2020 Chou interned at Mila, developing end-to-end speech recognition recipes for the SpeechBrain toolkit.2

Chou began the PhD at TTIC with Karen Livescu in April 2021. Chou's doctoral work includes a layer-wise analysis of wav2vec 2.0 representations, AV2Wav for diffusion-based audio-visual speech enhancement, and Flow-SLM, a spoken language model that learns linguistic and acoustic information together through a flow-matching objective.21

Chou's more recent work compares speech, speech-text, and text language models and studies distilling text language models into speech-to-speech models. Industry internships include transducer-based streaming speech translation at Microsoft in 2024 and robustness evaluation of audio-video-text language models at Meta in 2025.2

Work and contributions

  • Toward Joint Language Modeling for Speech Units and Text Published research

    First author of this 2023 paper with Wei-Ning Hsu, Karen Livescu, Michael Auli, and others; Chou's CV describes the joint interleaved language model for discrete speech units and text as work from the 2022 Meta AI research internship.32

  • Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling Published research

    First author, with J. Zhou and Karen Livescu, of this ASRU 2025 paper introducing a spoken language model trained with a flow-matching objective; it received the ASRU 2025 best student paper award.2

Timeline

  1. Published multi-target voice conversion without parallel data at Interspeech 2018.2
  2. Began a research internship at Mila, building speech recognition recipes for SpeechBrain.2
  3. Began PhD studies at the Toyota Technological Institute at Chicago, advised by Karen Livescu.2
  4. Began a research internship at Meta AI with mentor Wei-Ning Hsu.2
  5. Posted Toward Joint Language Modeling for Speech Units and Text, later in Findings of EMNLP 2023.32
  6. Began a research internship at Microsoft on streaming speech translation.2
  7. Presented Flow-SLM at ASRU 2025, where it received the best student paper award.2
  8. Began a research internship at Meta on multimodal language model robustness.2

Other documented roles

Roles the sources document that are not confirmed as current.

  • Research Intern (2022, Meta AI; 2025, Meta), Meta2
  • Research Intern (2024), Microsoft2

Honors and recognition

  • ASRU Best Student Paper Award · IEEE Automatic Speech Recognition and Understanding Workshop, 20252
  • ASRU Best Student Paper Award · IEEE Automatic Speech Recognition and Understanding Workshop, 20232

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

4 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Ju-Chieh Chou — TTIC homepageJu-Chieh Chou (Toyota Technological Institute at Chicago) · Official page · accessed Oct 21, 2026
  2. Ju-Chieh Chou — CV (last updated 2026-10-01)Ju-Chieh Chou · Official page · published Oct 1, 2026 · accessed Oct 21, 2026
  3. Toward Joint Language Modeling for Speech Units and Text (arXiv 2310.08715)arXiv · Paper · published Oct 12, 2023 · accessed Oct 21, 2026
  4. Karen Livescu — TTIC homepage (current graduate students)Karen Livescu (Toyota Technological Institute at Chicago) · Official page · accessed Oct 21, 2026