Guan-Ting is currently a Ph.D. student at Speech Processing and Machine Learning Lab, National Taiwan University (NTU), under the guidance of Prof. Hung-yi Lee. His research interest includes Speech LLM and Spoken Language Understanding and Generation.

Guan-Ting has published 10+ papers at top-tier Speech/NLP conferences (ACL, EMNLP, ICASSP, INTERSPEECH, and IEEE SLT) as the first or co-first author. Notably, he won the Best Paper Award at IEEE SLT 2022 in Doha, Qatar. Additionally, he serves as an official reviewer for multiple top conferences (ICLR, ACL, EMNLP, ICASSP, etc.).

Guan-Ting has several industrial research experience: He is currently an Student Researcher @ Google DeepMind (New York) in 2025 Spring. He is an incoming Research Scientist Intern @ Meta GenAI (Menlo Park) in 2025 Fall.

Previously, in 2024 summer, he interned with Amazon’s AGI-Speech team in Seattle, USA, working on Align-SLM, which enhances end-to-end spoken language models with RL. In 2023 summer, he worked with the Alexa Speech Recognition LM team on paralinguisic-enhanced LLM in Seattle, USA. In 2022 summer, he collaborated with Amazon Alexa on Acoustic Event Classification in Cambridge, USA.

For more details, please see the [CV].

Beyond academia, he enjoys singing 🎤, photography 📷, and watching MLB games ⚾️.

Update 🚨

• (03/2025) We release the Full-Duplex-Bench, which is the first benchmark that evaluates the full-duplex spoken dialogue models on turn-taking interaction.
• (11/2024) The preprint of Align-SLM is released, which is the first RLAIF framework for end-to-end textless spoken language models with state-of-the-art performance on SLM benchmarks!
• (09/2024) Continual TTA and Emphasized-Talk are accepted by EMNLP 2024 (one as main and one as findings).
• (05/2024) Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations is accepted by ACL 2024 as the main conference paper!
• (01/2024) Received IEEE Signal Processing Society Travel Grant for participating ICASSP 2024!
• (12/2023) Three papers are accepted by ICASSP 2024 (one first-author and two co-author). See you in Seoul!
• (02/2023) My internship work with Amazon Alexa is accepted by ICASSP 2023!
• (01/2023) Our paper “On the Utility of Self-supervised Models for Prosody-related Tasks”, cooperating with Prof. Nigel Ward of UTEP, won the Best Paper Award of IEEE SLT 2022!
• (07/2022) Received ISCA Travel Grants for Interspeech 2022.
• (06/2022) Two first-author papers are accepted at Interspeech 2022.

Education

• Ph.D. in Communication Engineering, EECS, National Taiwan University [2021 - Present]
  • Advisor: Prof. Hung-yi Lee
  • GPA: 4.24/4.3; Ranking: 15/158
  • Transferred from M.S. program in Feb. 2023.

Selected Publications & Preprints

(For full publication list, please see the Google Scholar).

Speech/Text Large Language Models

• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
  Guan-Ting Lin, Jiachen Lian_(co-second), Tingle Li_(co-second), Qirui Wang_(co-second), Gopala Anumanchipalli, Alexander H. Liu, Hung-yi Lee
  arXiv preprint
  paper
• Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback
  Guan-Ting Lin, Prashanth Gurunath Shivakumar, Aditya Gourav, Yile Gu, Ankur Gandhe, Hung-yi Lee, Ivan Bulyko
  arXiv preprint
  paper
• Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations
  Guan-Ting Lin, Cheng-Han Chiang, Hung-yi Lee
  ACL 2024
  paper / data
• Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue
  Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang, Yile Gu, Shalini Ghosh, Andreas Stolcke, Hung-yi Lee, Ivan Bulyko
  ICASSP 2024
  paper
• Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?
  Guan-Ting Lin, Hung-yi Lee
  EMNLP 2024 Findings
  paper / data

Self-supervised Speech Model

• On the Utility of Self-supervised Models for Prosody-related Task
  Guan-Ting Lin_(co-first), Chi-Luen Feng_(co-first), Wei-Ping Huang, Yuan Tseng, Tzu-Han Lin, Chen-An Li, Hung-yi Lee, Nigel G. Ward
  SLT 2022 (Best Paper Award)
  paper / code
• Introducing Semantics into Speech Encoders
  Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim, Zhaojiang Lin, Akshat Shrivastava, Shang-Wen Li, Liang-Hsuan Tseng, Alexei Baevski, Guan-Ting Lin, Hung-yi Lee, Yizhou Sun, Wei Wang
  ACL 2023
  paper
• SUPERB: Speech processing Universal PERformance Benchmark
  Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
  Interspeech 2021
  paper / code
• Analyzing the Robustness of Unsupervised Speech Recognition
  Guan-Ting Lin_(co-first), Chan-Jan Hsu_(co-first), Da-Rong Liu, Hung-Yi Lee, Yu Tsao
  ICASSP 2022
  paper / code

Spoken Language Understanding and Spoken Question Answering

• SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering
  Chyi-Jiunn Lin, Guan-Ting Lin, Yung-Sung Chuang, Wei-Lun Wu, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-shan Lee
  ICASSP 2024
  paper
• Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks
  Kevin Everson, Yile Gu, Huck Yang, Prashanth Gurunath Shivakumar, Guan-Ting Lin, Jari Kolehmainen, Ivan Bulyko, Ankur Gandhe, Shalini Ghosh, Wael Hamza, Hung-yi Lee, Ariya Rastrow, Andreas Stolcke
  ICASSP 2024
  paper
• Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target
  Guan-Wei Wu_(co-first), Guan-Ting Lin_(co-first), Shang-Wen Li, Hung-yi Lee
  Interspeech 2023
  paper
• DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering
  Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung, Shu-wen Yang, Hsuan-Jui Chen, Shuyan Dong, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-shan Lee
  Interspeech 2022 (Poster)
  paper / code

End-to-end ASR Test-time Adaptation

• Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
  Guan-Ting Lin_(co-first), Wei-Ping Huang_(co-first), Hung-yi Lee
  EMNLP 2024
  paper
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition
  Guan-Ting Lin, Shang-Wen Li, Hung-Yi Lee
  Interspeech 2022 (Oral)
  paper / code

Audio Event Classification

• Weight-sharing Supernet for Searching Specialized Acoustic Event Classification Networks Across Device Constraints
  Guan-Ting Lin, Qingming Tang, Chieh-Chi Kao, Viktor Rozgic, Chao Wang
  ICASSP 2023
  paper

Experience

• Student Researcher, Google DeepMind, New York, United States
  [2025/2 - Present]
  • Gemini Speech Team.
• Applied Scientist II Intern, Amazon AGI, Seattle, United States
  [2024/6 - 2024/9]
  • AGI-Speech Research Team
  • End-to-end Spoken Language Models.
• Applied Scientist II Intern, Amazon Alexa, Seattle, United States
  [2023/6 - 2023/9]
  • Speech Recognition LM Research Team
  • Paralinguistics-enhanced Large Language Model on spoken dialogue.
• Applied Scientist I Intern, Amazon Alexa, Cambridge, United States
  [2022/7 - 2022/10]
  • Manager: Chieh-Chi Kao / Mentor: Qingming Tang
  • Develop Once-for-all Network Architecture Search techniques on audio event classification.
• Visiting Reseacher, 8th JASLT Summer Workshop, Johns Hopkins University, Baltimore, United States
  [2022/6 - 2022/7]
  • Work with Prof. Nigel Ward on self-supervised pre-training for prosody.

Award

• IEEE Signal Processing Society Travel Grant @ ICASSP 2024
• Best paper award @ IEEE SLT 2022
• NTU Elite Doctoral Scholarship
• GICE Elite Doctoral Scholarship with NVIDIA
• ISCA travel grant @ Interspeech 2022
• Appier top-tier conference scholarship
• Dean’s list * 3 @ NTHU
• Phi Tau Phi Award @ NTHU
• The Zhu Shun Yi He Qin Scholarship @ NTHU

Academic Services

• Official Reviewer: ICLR’24’25, NeurIPS’24, ACL’24, EMNLP’24, NAACL’23’24, ICASSP’23’24, ISCSLP’22’23’24, COLING’25