Chin-Jou Li

Now: Pittsburgh, PA, USA

Home: Hsinchu, Taiwan

Hi! I’m Chin-Jou, a first-year PhD student at the Language Technologies Institute, Carnegie Mellon University, supervised by David R. Mortensen and Shinji Watanabe. I was initially drawn to CS by its potential to improve people’s lives. My interests now center on human understanding and communication, particularly through multilingual and cross-lingual speech technologies.

In my spare time, I enjoy reading and occasionally drawing.

News

Sep 2026	Two papers accepted to SLT: HARP: Agentic Hybrid Retrieval and Analysis for Long-Form Audio and Phone Segmentation and Recognition through Phonological Activation Mapping
Aug 2026	I spent my summer at JSALT in Baltimore, MD, working with the Omnimodal Encoder team. I had a great time and learned a lot!
May 2026	Our papers An Empirical Recipe for Universal Phone Recognition & Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson’s Disease are accepted by Interspeech 2026

Selected publications

ACL

PRiSM: Benchmarking Phone Realization in Speech Models

Shikhar Bharadwaj^*, Chin-Jou Li^*, Yoonjae Kim^*, Kwanghee Choi, Eunjung Yeo, and 11 more authors

In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

Abs DOI

Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis. Despite prolonged efforts in developing PR systems, current evaluations only measure surface-level transcription accuracy. We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception through intrinsic and extrinsic evaluation of PR systems. PRiSM standardizes transcription-based evaluation and assesses downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. We find that diverse language exposure during training is key to PR performance, encoder-CTC models are the most stable, and specialized PR systems still outperform LALMs. PRiSM releases code, recipes, and datasets to move the field toward multilingual speech models with robust phonetic ability.
ACL

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model

Chin-Jou Li^*, Kalvin Chang^*, Shikhar Bharadwaj, Eunjung Yeo, Kwanghee Choi, and 3 more authors

In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

Abs DOI

Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion (P2G). Despite their conceptual similarity, these tasks have largely been studied in isolation, each relying on task-specific architectures and datasets. In this paper, we introduce POWSM (Phonetic Open Whisper-style Speech Model), the first unified framework capable of jointly performing multiple phone-related tasks. POWSM enables seamless conversion between audio, text (graphemes), and phones, opening up new possibilities for universal and low-resource speech processing. Our model outperforms or matches specialized PR models of similar size (Wav2Vec2Phoneme and ZIPA) while jointly supporting G2P, P2G, and ASR. Our training data, models, and code are released to foster open science.