Speaker Trait Evaluation (ARTS)
May 2025 - Present · USC - JHU - Meaning Company
- Benchmark and propose a novel approach to measure pronunciation accuracy.
- Proposed a speaker poisoning framework that erases a target speaker's voice-cloning capability in zero-shot TTS to protect against unauthorized voice generation. (1 COLM ReData Workshop 2026 publication)
- Developed frameworks to develop state-of-the-art speech emotion recognition (SER) for predicting both emotional attributes and categorical emotions. They achieved 1st rank in emotional attributes and 2nd rank in categorical attributes in Naturalistic Conditions Challenge (2 Interspeech2025 publications)