I am currently a Senior Researcher at Tencent Singapore under the ‘Project Up’ (青云计划) Talent Programme, specializing in Speech Synthesis (Speech GenAI). Previously, I obtained my Ph.D. from the National University of Singapore (NUS), where I was supervised by Prof. Li Haizhou and Prof.Mike Z. SHOU. Before joining Tencent, I worked as a Senior Research Engineer at the Agency for Science, Technology and Research (A*STAR), Singapore, focusing on Speech-LLM (MERaLiON Team), Speech Anti-Spoofing (Speech DeepFake Detection), and Speaker Recognition.

My research interests include text-to-speech, speaker recognition, anti-spoofing, speech-LLM, etc. I have published more than 20 papers in the top international AI conferences and journals such as NeurIPS, IEEE TIFS, IEEE TASLP, EMNLP, IEEE SPL, IEEE ICASSP, INTERSPEECH.

🔍 Research Area

Speech Processing: Text-to-Speech (TTS), Speaker Recognition, Speech Foundation Model, Anti-spoofing / DeepFake Detection, Target Speaker Extraction

Multi-modal Processing: Speech-LLM, Audio-visual

Algorithm: Self-supervised Learning, Disentanglement Learning

🎓 Education

2021.01 - 2025.01, Ph.D. in Speech Processing, National University of Singapore (NUS), Singapore.
2018.07 - 2019.06, M.Sc. in Electronic and Computer Engineering (Specialization in Computer Engineering), National University of Singapore (NUS), Singapore.

💼 Work Experience

2025.02 - Now, Senior Researcher, ‘Project Up’ (青云计划) Talent Programme, Tencent, Singapore.
2020.09 - 2025.02, Senior Research Engineer, Agency for Science, Technology and Research (A*STAR), Singapore.
2019.06 - 2020.08, AI Scientist, PENSEES R&D Center, Singapore

📜 Publication

⭐ Selected Publications

T. Liu, D. T. Truong, R. K. Das, K. A. Lee, H. Li, Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing, IEEE Transactions on Information Forensics and Security (TIFS), 2025. 🔗[IEEE, arXiv, Code & Models]
T. Liu, K. A. Lee, Q. Wang, H. Li, Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification, IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2024. 🔗[IEEE, arXiv, pre-trained models & simple inference, train & test code, ONNX]
T. Liu, K. A. Lee, Q. Wang, H. Li, Disentangling Voice and Content with Self-Supervision for Speaker Recognition, Advances in Neural Information Processing Systems (NeurIPS), 2023. 🔗[NeurIPS, arXiv]
T. Liu, R. K. Das, K. A. Lee, H. Li, MFA: TDNN with multi-scale frequency-channel attention for text-independent speaker verification with short utterances, IEEE ICASSP, oral, 2022. 🔗[IEEE, arXiv, code]
[🌊MERaLiON🦁] M. Huzaifah*, G. Lin*, T. Liu*, H. B. Sailor*, K. M. Tan*, T. K. Vangani*, Q. Wang*, J. H. M. Wong*, N. F. Chen, A. T. Aw (MERaLiON Team), MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond, 2024. 🔗[arXiv, 🤗Hugging Face]

Speech-LLM Pretraining & Reasoning

Q. Wang, H. B. Sailor, T. Liu, …, Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data, EMNLP (findings), 2025. 🔗[arXiv, ACL Anthology]
Q. Wang, H. B. Sailor, J. H. Wong, T. Liu, …, Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models, IEEE ASRU, 2025. 🔗[IEEE (soon), arXiv]
Q. Wang, H. B. Sailor, T. Liu, A. T. Aw, Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation, INTERSPEECH, 2025. 🔗[ISCA, arXiv, dataset(🤗Hugging Face)]
[🌊MERaLiON🦁] M. Huzaifah*, G. Lin*, T. Liu*, H. B. Sailor*, K. M. Tan*, T. K. Vangani*, Q. Wang*, J. H. M. Wong*, N. F. Chen, A. T. Aw (MERaLiON Team), MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond, 2024. 🔗[arXiv, 🤗Hugging Face]
(Under Review) L. Xue, …, T. Liu, …, Audio-FLAN: A Preliminary Release, 2025. 🔗[arXiv, Dataset(🤗Hugging Face), Github]

Speaker Recognition & Target Speaker Extraction

(Best Paper Award) R. Tao, Z. Shi, Y. Jiang, T. Liu, H. Li, Voice Conversion Augmentation for Speaker Recognition on Defective Datasets, APSIPA ASC, 2025. 🔗[arXiv, IEEE Xplore]
Y. Ma, S. Wang, T. Liu, H. Li, PhiNet: Speaker Verification with Phonetic Interpretability, IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2025. 🔗[IEEE Xplore]
T. Liu, R. Tao, Q. Wang, …, Interpolating Speaker Identities in Embedding Space for Data Expansion, APSIPA ASC, 2025. 🔗[arXiv, IEEE Xplore]
Y. Ma, S. Wang, T. Liu, H. Li, ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification, IEEE Signal Processing Letters (SPL), 2025. 🔗[IEEE, arXiv, code]
K. Zhang, M. Borsdorf, T. Liu, S. Wang, Y. Wei, H. Li, Speaker Extraction with Verification of Present and Absent Target Speakers, Journal of Shanghai Jiaotong University (Science), 2025. 🔗[Paper Link]
T. Liu, Advances in Robust and Practical Speaker Verification, 2025.
T. Liu, K. A. Lee, Q. Wang, H. Li, Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification, IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2024. 🔗[IEEE, arXiv, pre-trained models & simple inference, train & test code, ONNX]
T. Liu, K. A. Lee, Q. Wang, H. Li, Disentangling Voice and Content with Self-Supervision for Speaker Recognition, Advances in Neural Information Processing Systems (NeurIPS), 2023. 🔗[NeurIPS, arXiv]
Q. Wang, K. A. Lee, T. Liu, Incorporating Uncertainty from Speaker Embedding Estimation to Speaker Verification, IEEE ICASSP, oral, 2023. 🔗[IEEE, arXiv]
T. Liu, R. K. Das, K. A. Lee, H. Li, MFA: TDNN with multi-scale frequency-channel attention for text-independent speaker verification with short utterances, IEEE ICASSP, oral, 2022. 🔗[IEEE, arXiv, code]
T. Liu, R. K. Das, K. A. Lee, H. Li, Neural acoustic-phonetic approach for speaker verification with phonetic attention mask, IEEE Signal Processing Letters (SPL), 2022. 🔗[IEEE]
Q. Wang, K. A. Lee, T. Liu, Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?, INTERSPEECH, oral, 2022. 🔗[ISCA, arXiv]
T. Liu, R. K. Das, M. C. Madhavi, S. Shen, H. Li, Speaker-Utterance Dual Attention for Speaker and Utterance Verification, INTERSPEECH, 2020. 🔗[ISCA, arXiv]
T. Liu, M. C. Madhavi, R. K. Das, H. Li, A Unified Framework for Speaker and Utterance Verification, INTERSPEECH, 2019. 🔗[ISCA, code]

Speech DeepFake Detection / Antispoofing <!—

D. T. Truong, T. Liu, …, Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection, IEEE ICASSP, 2026. 🔗[arXiv] –>
T. Liu, D. T. Truong, R. K. Das, K. A. Lee, H. Li, Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing, IEEE Transactions on Information Forensics and Security (TIFS), 2025. 🔗[IEEE, arXiv, Code & Models]
T. Liu, L. Zhang, R. K. Das, Y. Ma, R. Tao, H. Li, How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?, INTERSPEECH, oral, 2024. 🔗[ISCA, arXiv]
Z. Pan, T. Liu, H. B. Sailor, Q. Wang, Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection, INTERSPEECH, oral, 2024. 🔗[ISCA, arXiv, code]
T. Liu, I. Kukanov, Z. Pan, Q. Wang, H. B. Sailor, K. A. Lee, Towards Quantifying and Reducing Language Mismatch Effects in Cross-lingual Speech Anti-Spoofing, IEEE SLT, 2024.🔗[IEEE, arXiv]
A. Guragain*, T. Liu*, Z. Pan, H. B. Sailor, Q. Wang, Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024, IEEE SLT, (co-first author*), 2024. 🔗[IEEE, arXiv, code] <!—
D. T. Truong, T. Liu, …, QAMO: Quality-aware Multi-centroid One-class Learning For Speech Deepfake Detection, under review. 🔗[arXiv] –>

Audio-Visual

J. Meng, H. B. Sailor, Q. Wang, T. Liu, …, Exploring audio-visual fusion methods in foundation model-based deception detection, APSIPA ASC, 2025. 🔗[IEEE Xplore]

💻 Open Source Contributions

WeSpeaker
AudioLLM
Audio-FLAN
Nes2Net
MERaLiON [🤗Hugging Face]

🌟 Others

🥇 Awards🥈🥉🏅🎖️

🥇Best Paper Award (1 paper only), APSIPA, 2025 (Co-author)
🥈Sliver Award, Tencent AI Application Award, Tencent, 2025
🥇Best Student Paper Award (1 recipient annually), Pattern Recognition and Machine Intelligence Association (PREMIA), 2024
🥇Best Student Paper Award (2 recipients annually), Nanyang Speech Technology Forum (NSTF), 2024
🥉3rd place winner out of 49 teams in the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024 @ IEEE SLT, 2024
🥇Best Paper Award in 2023 International Doctoral Forum (CUHK & Microsoft), 2023
🥇Travel Grant Award (Top Tier), Chinese and Oriental Languages Information Processing Society (COLIPS), 2023
🎖️5th place winner out of 128 teams in NIST Face Recognition Vendor Test (FRVT) - Face Mask Effects, 2020
Outstanding Achievement Award under the Research Domain, PENSEES Singapore, 2020

🏛️ Academic Service

Virtual Session Chair @ IEEE IALP, 2023
Program Committee @ IEEE ISCSLP, 2022
Volunteer @ IEEE ICASSP, 2022

📝 Reviewer

Journal/Transactions/Letters:

Neural Networks ‘25
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP) ‘25
IEEE Transactions on Dependable and Secure Computing (TDSC) ‘25
IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM) ‘25
Computer Speech & Language ‘24~’25
IEEE Signal Processing Letters (SPL) - ‘23~’25

Conference: