Zhuoyan Tao (Terry)

  • Carnegie Mellon · M.S. student, LTI
  • Apple · Software engineering intern, 2026

I'm Terry. I work with Prof. Shinji Watanabe at WavLab on recovering speech from damaged audio and predicting how it sounds to listeners. I'm currently the lead student researcher on an Amazon AGI project on target-speaker speech restoration.

Seeking Summer 2027 research or ML engineering internships in speech and audio

Portrait of Zhuoyan (Terry) Tao

Selected research

TurnBench turn-taking overview

IEEE SLT 2026

TurnBench — evaluating conversational turn-taking

Freeman Jiang, Ramon Sanabria, …, Zhuoyan Tao, …, Hung-yi Lee, Shinji Watanabe

A benchmark for when conversational systems should speak or wait, with 30 hours of hand-labeled conversation and 14 systems benchmarked.

Off-target posterior mass and probe gain prediction

JASA-EL · Under review

When does language-ID fine-tuning help?

Zhuoyan Tao, Aditya Kommineni, Shrikanth Narayanan

A single training-free number, computed from language-ID posteriors, that forecasts whether fine-tuning a diarization probe will pay off.

PDF ↗︎

Open source

Background

Carnegie Mellon2025–present M.S. student · speech research at WavLab

M.S. in Intelligent Information Systems, expected Dec 2027. Speech research at WavLab with Prof. Shinji Watanabe.

AppleSummer 2026 Software engineering intern · satellite connectivity

Built simulation tooling with ~1000× higher experiment throughput.

USCGraduated 2026 B.S. Computer Science · B.S. Applied and Computational Mathematics

Trustee Scholar (full-tuition merit scholarship); graduated magna cum laude. Multilingual speech research with Prof. Shrikanth Narayanan at SAIL.

Outside research, I led the audio team for Bone Boy, a game released on Steam, and taught multivariable calculus review sessions. Full experience and honors in my résumé ↗︎

Contact

For research collaborations or Summer 2027 internships: terrytao@andrew.cmu.edu.