About Me

Hi, I’m Thanathai, a third-year PhD student at the University of Southern California and a member of the Signal Analysis and Interpretation Laboratory (SAIL). I research speech processing, focusing on controllable text-to-speech (TTS) and speaker trait evaluation. I am advised by Shrikanth Narayanan.

My research focuses on speech processing, particularly controllable speech generation, spanning both generation and evaluation. I began by exploring accent-controllable text-to-speech (TTS), combining linguistic knowledge with engineering approaches. I have also helped develop models for evaluating speaker traits and new metrics for measuring trait leakage from speaker embeddings and assessing pronunciation accuracy. In addition, I explore speech privacy through speaker poisoning frameworks and membership inference attacks.

Before starting my PhD, I received my Bachelor's Degree in Computer Engineering from Chulalongkorn University, Thailand, where I also worked as a research assistant with Ekapol Chuangsuwanich on speaker verification and anti-spoofing. I've also had the opportunity to intern at Tencent Thailand in 2021, where I worked on news and song recommendation systems.

News

Projects

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)
Speech Emotion RecognitionSpeech PrivacyPronunciation Accuracy

Controlled Text-to-Speech (ARTS)

Oct 2024 - Present · USC - JHU - Meaning Company

  • Proposed Accent Vector, a controllable accent manipulation method for multilingual TTS that requires no accented training data.
  • Developing learning-free framework for multilingual TTS on British, Spanish, and Indian Accent.
  • Analyzed the effect of speaker embedding on accent strength using phonemes rules to control the effect. (1 ICASSP2026 publication)
Accent ConversionSpeech Emotion RecognitionTTSSpeech Security

Speaker Recognition and Anti-spoofing System

Aug 2022 - May 2024 · Chulalongkorn University

  • Proposed an approach to amplify artifacts in spoofed utterances using speech enhancement and show its robustness on different countermeasures and speech enhancement models (1 Interspeech2025 publication).
  • Proposed a new normalization layer to address the problem of mismatched emotions and languages in speaker verification. (1 Interspeech2023 publication).
Speaker RecognitionAnti-spoofingSpeech Enhancement

Awards & Honors

  • Student Grant

    May 2026

    Awarded a Student Travel Grant for ICASSP 2026.

  • SER Challenge

    Aug 2025

    Rank 1st in attribute prediction and 2nd in category prediction on the Speech Emotion Recognition in Naturalistic Conditions Challenge.

  • Student Grant

    Aug 2023

    Awarded a Student Travel Grant for Interspeech 2023.

Academic Service

Reviewer for the following venues:

  • Interspeech 2026
  • IEEE Spoken Language Technology Workshop (SLT) 2026
  • COLM ReData Workshop 2026