Burin Naowarat

Burin Naowarat

burin.naowarat@ed.ac.uk

I wonder how intelligence emerges and is represented in human and machine minds. I am currently exploring these questions through interpretability research, using geometry to understand and learn from hidden structures in neural network representations.

I’m a PhD student at the Centre for Speech Technology Research (CSTR) in the School of Informatics at the University of Edinburgh, supervised by Sharon Goldwater and Hao Tang. My current work identifies and examines emergent structures in deep speech models that correspond to different aspects of speech, such as what is said, who is speaking, and how speech unfolds over time.

Before starting my PhD, I completed a research master’s degree focused on ASR at Chulalongkorn University, supervised by Ekapol Chuangsuwanich. During my master’s, I interned with Amazon Alexa in Cambridge, UK. I later worked as a language modelling engineer for on-device ASR systems at Cerence.

Portrait of Burin Naowarat

Publications

View on Google Scholar ↗

  1. A framework for analyzing concept representations in neural models

    Burin Naowarat, Hao Tang, and Sharon Goldwater.

    CoNLL, 2026. Paper ↗ Code ↗ Poster ↗

  2. Effective Training of Attention-based Contextual Biasing Adapters with Synthetic Audio for Personalised ASR

    Burin Naowarat, Philip Harding, Pasquale D’Alterio, Sibo Tong, and Bashar Awwad Shiekh Hasan.

    Interspeech, 2023. Paper ↗

  3. Word-level Confidence Estimation for CTC Models

    Burin Naowarat, Thananchai Kongthaworn, and Ekapol Chuangsuwanich.

    Interspeech, 2023. Paper ↗ Code ↗

  4. Thai Dialect Corpus and Transfer-based Curriculum Learning Investigation for Dialect Automatic Speech Recognition

    Artit Suwanbandit, Burin Naowarat, Orathai Sangpetch, and Ekapol Chuangsuwanich.

    Interspeech, 2023. Paper ↗ Data ↗

  5. Context Conditioning via Surrounding Predictions for Non-Recurrent CTC Models

    Burin Naowarat, Chawan Piansaddhayanon, and Ekapol Chuangsuwanich.

    IEEE Access, 2023. Paper ↗

  6. Spectral and Latent Speech Representation Distortion for TTS Evaluation

    Thananchai Kongthaworn, Burin Naowarat, and Ekapol Chuangsuwanich.

    Interspeech, 2021. Paper ↗

  7. Set Prediction in the Latent Space

    Konpat Preechakul, Chawan Piansaddhayanon, Burin Naowarat, Tirasan Khandhawit, Sira Sriswasdi, and Ekapol Chuangsuwanich.

    NeurIPS, 2021. Paper ↗ Code ↗

  8. Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss

    Burin Naowarat, Thananchai Kongthaworn, Korrawe Karunratanakul, Sheng Hui Wu, and Ekapol Chuangsuwanich.

    ICASSP, 2021. Paper ↗