Lingwei Meng

About

I am a research scientist at ByteDance Seed. Prior to joining ByteDance, I worked as a research intern at Microsoft Research Asia. I received my Ph.D. degree in speech & language processing from Human-Computer Communications Laboratory (HCCL), The Chinese University of Hong Kong (CUHK), supervised by Prof. Helen Meng.

My research interests focus on language modeling for speech synthesis and the integration of speech with large language models. I am also working on speech processing and recognition.

Highlights

[Aug 2025]  I started my career at ByteDance Seed as a Research Scientist.
[Jul 2025]  I defended my Ph.D. thesis
[Jul 2025]  Two papers, [FELLE] & [PALLE], have been accepted to ACM Multimedia 2025
[May 2025]  We present [MELLE] (ACL 2025 Main), a pioneer effort in continuous-value token-based language modeling for TTS
[May 2025]  Three papers have been accepted to ISCA INTERSPEECH 2025
[Apr 2025]  Our [paper] is the only winner of the 2025 IEEE Ganesh N. Ramaswamy Memorial Student Grant
[Jan 2025]  We present [ARLON] (ICLR 2025), boosting diffusion transformers with autoregressive models for long video generation
[Dec 2024]  Two papers have been accepted to IEEE ICASSP 2025, including one first-authored [paper]
[Dec 2024]  I participated in writing the excellent [survey] on Next Token Prediction Towards Multimodal Intelligence
[Jun 2024]  We propose [WavLLM], a robust and adaptive Speech LLM achieving SOTA performance on various speech-related tasks
[Jun 2024]  Three papers have been accepted to ISCA INTERSPEECH 2024, including one first-authored [paper]
[Jan 2024]  Two papers have been accepted to IEEE ICASSP 2024

Experiences

• Aug. 2025 - PresentResearch Scientist, ByteDance Seed
  Studying large audio language models

• Nov. 2023 - Feb. 2025Research Intern, General Artificial Intelligence Group, Microsoft Research Asia
  Studying language modeling for speech synthesis; integrating speech with large language models
  Working closely with Dr. Shujie Liu, Dr. Long Zhou, and Dr. Furu Wei

• Aug. 2021 - Aug. 2025Ph.D., Human-Computer Communications Laboratory, The Chinese University of Hong Kong
  Supervised by Prof. Helen Meng , working closely with Prof. Xunying Liu and Prof. Xixin Wu

Selected Publications

[Google Scholar]

• MELLE: Autoregressive Speech Synthesis without Vector Quantization   |   [demo]
  Lingwei Meng, Long Zhou, Shujie Liu, Sanyuan Chen, Bing Han, Shujie Hu, Yanqing Liu, Jinyu Li, Sheng Zhao, Xixin Wu,
  Helen Meng, Furu Wei
  The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025

• Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions   |   [code]
  Lingwei Meng, Shujie Hu, Jiawen Kang, Zhaoqing Li, Yuejiang Wang, Wenxuan Wu, Xixin Wu, Xunying Liu, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025

• Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System   |   [code]
  Lingwei Meng, Jiawen Kang, Yuejiao Wang, Zengrui Jin, Xixin Wu, Xunying Liu, Helen Meng
  ISCA INTERSPEECH, 2024

• A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One   |   [slides] [video]
  Lingwei Meng, Jiawen Kang, Mingyu Cui, Yuejiao Wang, Xixin Wu, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

• Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
  Lingwei Meng, Jiawen Kang, Mingyu Cui, Haibin Wu, Xixin Wu, Helen Meng
  ISCA INTERSPEECH, 2023

• FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
  Hui Wang, Shujie Liu, Lingwei Meng, Jinyu Li, Yifan Yang, Shiwan Zhao, Haiyang Sun, Yanqing Liu, Haoqin Sun, Jiaming Zhou,
  Yan Lu, Yong Qin
  ACM MM, 2025

• Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC
  Jiawen Kang, Lingwei Meng, Mingyu Cui, Yuejiao Wang, Xixin Wu, Xunying Liu, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
  (The only winner of the 2025 lEEE Ganesh N. Ramaswamy Memorial Student Grant)

• ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation   |   [demo]
  Zongyi Li, Shujie Hu, Shujie Liu, Long Zhou, Jeongsoo Choi, Lingwei Meng, Xun Guo, Jinyu Li, Hefei Ling, Furu Wei
  The Thirteenth International Conference on Learning Representations (ICLR), 2024

• WavLLM: Towards Robust and Adaptive Speech Large Language Model   |   [code]
  Shujie Hu, Long Zhou, Shujie Liu, Sanyuan Chen, Lingwei Meng, Hongkun Hao, Jing Pan, Xunying Liu, Jinyu Li, Sunit Sivasankaran, Linquan Liu, Furu Wei
  EMNLP Findings, 2024

• VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment   |   [demo]
  Bing Han, Long Zhou, Shujie Liu, Sanyuan Chen, Lingwei Meng, Yanming Qian, Yanqing Liu, Sheng Zhao, Jinyu Li, Furu Wei
  arXiv, 2024

• Large Language Model-based FMRI Encoding of Language Functions for Subjects with Neurocognitive Disorder
  Yuejiao Wang, Xianmin Gong, Lingwei Meng, Xixin Wu, Helen Meng Sheng Zhao, Jinyu Li, Furu Wei
  ISCA INTERSPEECH, 2024

• Cross-Speaker Encoding Network for Multi-Talker Speech Recognition   |   [code]
  Jiawen Kang, Lingwei Meng, Mingyu Cui, Haohan Guo, Xixin Wu, Xunying Liu, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024

• UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization
  Yuejiao Wang, Xixin Wu, Disong Wang, Lingwei Meng, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024

• Spoofing-Aware Speaker Verification by Multi-Level Fusion
  Haibin Wu, Lingwei Meng, Jiawen Kang, Jinchao Li, Xu Li, Xixin Wu, Hung-yi Lee, Helen Meng
  ISCA INTERSPEECH, 2022

• Exploring Linguistic Feature and Model Combination for Speech Recognition Based Automatic AD Detection
  Yi Wang, Tianzi Wang, Zi Ye, Lingwei Meng, Shoukang Hu, Xixin Wu, Xunying Liu, Helen Meng
  ISCA INTERSPEECH, 2022

• The CUHK-Tencent Speaker Diarization System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
  Naijun Zheng, Na Li, Xixin Wu, Lingwei Meng, Jiawen Kang, Haibin Wu, Chao Weng, Dan Su, Helen Meng
  IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022

- Medical Image Analysis related journal papers:

• 2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: a Multi-Center Study
  Lingwei Meng, Di Dong, Xin Chen, Mengjie Fang, Rongpin Wang, Jing Li, Zaiyi Liu, Jie Tian
  IEEE Journal of Biomedical and Health Informatics (IEEE JBHI), 2021  (Impact Factor: 6.7)
  (ESI Highly Cited Paper)

• A Deep Learning Prognosis Model Help Alert for COVID-19 Patients at High-Risk of Death: a Multi-Center Study
  Lingwei Meng, Di Dong, Liang Li, Meng Niu, Yan Bai, Meiyun Wang, Xiaoming Qiu, Yunfei Zha, Jie Tian
  IEEE Journal of Biomedical and Health Informatics (IEEE JBHI), 2020  (Impact Factor: 6.7)

• Noninvasive Model for Predicting Future Ischemic Strokes in Patients with Silent Lacunar Infarction Using Radiomics
  Lingwei Meng#, Jiehua Su#, Di Dong#, Wenyan Zhuo, Jianming Wang, Libin Liu, Yi Qin, Ye Tian, Jie Tian, Zhaohui Li
  BMC Medical Imaging, 2020  (# denotes the co-first authorship.)  (Impact Factor: 2.9)

Challenges

• Rank 2/14IEEE ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) - Track 1

Activities

Serving as a reviewer for top journals and conferences, including IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), IEEE Journal of Selected Topics in Signal Processing (JSTSP), IEEE Journal of Biomedical and Health Informatics (JBHI), Pattern Recognition, International Conference on Learning Representations (ICLR), IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), ISCA INTERSPEECH, ACM Multimedia, among others.

Teaching Assistance

2021 - 2025, SEEM 3440, Operation Research II
2021 - 2025, AIST 3510 / SEEM 3510, Human-Computer Interaction