HL
Hexin Liu
eess.AScs.SDcs.CLcs.AIastro-ph.HEcs.CV3-hydroxypropionic acidAgglomerationaggregationAluminum hydride
On Valency
published · living versionsW_rh8e9wyt·v1 · currentpublished
Heard Enough to Act: Early Tool Calling in Spoken Dialogue Systems
with Yizhou Peng, Chen Chen, Donghang Wu, Eng Siong Chng
1 version
Preprints & journals
43 papers in the corpus · 2022–2026Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech2606.19381v1 · Yue Heng Yeo, Haoyang Li, Yizhou Peng et al.2026 · 0 citationsarXiv
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models2605.29209v1 · Xiangyu Zhang, Yuxin Li, Haoyang Zhang et al.2026 · 0 citationsarXiv
DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action2605.20755v2 · Haoyang Zhang, Jun Chen, Donghang Wu et al.2026 · 0 citationsarXiv
Step-Audio-R1.5 Technical Report2604.25719v2 · Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu et al.2026 · 0 citationsarXiv
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning2603.17837v5 · Donghang Wu, Tianyu Zhang, Yuxin Li et al.2026 · 0 citationsarXiv
Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision2603.07025v2 · Shreyas Gopal, Donghang Wu, Ashutosh Anshul et al.2026 · 0 citationsarXiv
The ICASSP 2026 Automatic Song Aesthetics Evaluation Challenge2601.07237v1 · Guobin Ma, Yuxuan Xia, Jixun Yao et al.2026 · 2 citationsarXiv
Improving Code-Switching Speech Recognition with TTS Data Augmentation2601.00935v1 · Yue Heng Yeo, Yuchen Hu, Shreyas Gopal et al.2026 · 1 citationarXiv
Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR2510.25150v1 · Shreyas Gopal, Ashutosh Anshul, Haoyang Li et al.2025 · 0 citationsarXiv
Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models2510.09592v2 · Donghang Wu, Haoyang Zhang, Jun Chen et al.2025 · 1 citationarXiv
Chronological Thinking in Full-Duplex Spoken Dialogue Language Models2510.05150v3 · Donghang Wu, Haoyang Zhang, Chen Chen et al.2025 · 1 citationarXiv
Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives2509.24310v2 · Hexin Liu, Haoyang Zhang, Qiquan Zhang et al.2025 · 2 citationsarXiv
Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods2509.13785v1 · Bingshen Mu, Pengcheng Guo, Zhaokai Sun et al.2025 · 0 citationsarXiv
Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study2507.04368v1 · Qiquan Zhang, Moran Chen, Zeyang Song et al.2025 · 1 citationWASPAA 2025
EASY: Emotion-aware Speaker Anonymization via Factorized Distillation2505.15004v2 · Jixun Yao, Hexin Liu, Eng Siong Chng et al.2025 · 2 citationsarXiv
Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning2504.20835v1 · Hongfei Xue, Yufeng Tang, Hexin Liu et al.2025 · 0 citationsarXiv
SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information2502.10950v2 · Xiangyu Zhang, Hexin Liu, Qiquan Zhang et al.2025 · 3 citationsarXiv
GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling2502.02942v1 · Jixun Yao, Hexin Liu, Chen Chen et al.2025 · 2 citationsarXiv
Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding2412.16507v3 · Jiahui Zhao, Hao Shi, Chenrui Cui et al.2024 · 5 citationsICASSP 2025
SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model2411.07751v2 · Xinyuan Qian, Jiaran Gao, Yaodan Zhang et al.2024 · 5 citationsarXiv
Selective State Space Model for Monaural Speech Enhancement2411.06217v1 · Moran Chen, Qiquan Zhang, Mingjiang Wang et al.2024 · 11 citationsarXiv
Insights into the Fragmentation of Aluminum Hydride and Its Effect on Combustion and Agglomeration of HTPB Propellant.39149773 · Jiang, Zhoufeng, Zhao, Fengqi, Qin, Zhao et al.2024 · 8 citationsACS applied materials & interfaces. 2024;16(34):45640-45659
Mamba in Speech: Towards an Alternative to Self-Attention2405.12609v6 · Xiangyu Zhang, Qiquan Zhang, Hexin Liu et al.2024 · 80 citationsarXiv
Aligning Speech to Languages to Enhance Code-switching Speech Recognition2403.05887v3 · Hexin Liu, Xiangyu Zhang, Haoyang Zhang et al.2024 · 16 citationsarXiv
The bright black hole X-ray binary 4U 1543-47 during 2021 outburst. A clear state transition from super-Eddington to sub-Eddington accretion revealed by Insight-HXMT2403.02874v1 · Pei Jin, Guobao Zhang, Yuexin Zhang et al.2024 · 12 citationsarXiv
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection2402.13276v2 · Xiangyu Zhang, Hexin Liu, Kaishuai Xu et al.2024 · 26 citationsarXiv
Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model2402.10642v2 · Xiangyu Zhang, Daijiao Liu, Hexin Liu et al.2024 · 6 citationsarXiv
Studies on the soft intermediate state X-ray flare of MAXI J1535-571 during its 2017 outburst2401.11466v1 · Ruican Ma, Lian Tao, Mariano M'endez et al.2024 · 2 citationsarXiv
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors2311.15954v1 · Shuyue Stella Li, Beining Xu, Xiangyu Zhang et al.2023 · 2 citationsarXiv
Generative error correction for code-switching speech recognition using large language models2310.13013v1 · Chen Chen, Yuchen Hu, Chao-Han Huck Yang et al.2023 · 4 citationsarXiv
Enhancing Code-switching Speech Recognition with Interactive Language Biases2309.16953v1 · Hexin Liu, Leibny Paola Garcia, Xiangyu Zhang et al.2023 · 24 citationsarXiv
Unidirectional brain-computer interface: Artificial neural network encoding natural images to fMRI response in the visual cortex.37808091 · Liang, Ruixing, Zhang, Xiangyu, Li, Qiong et al.2023 · 3 citationsArXiv. 2023
MERLIon CCS Challenge Evaluation Plan2305.19493v1 · Leibny Paola Garcia Perera, Y.H. Victoria Chua, Hexin Liu et al.2023 · 3 citationsarXiv
MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization2305.18881v1 · Victoria Y. H. Chua, Hexin Liu, Leibny Paola Garcia Perera et al.2023 · 10 citationsarXiv
Investigating model performance in language identification: beyond simple error statistics2305.18925v1 · Suzy J. Styles, Victoria Y. H. Chua, Fei Ting Woon et al.2023 · 1 citationarXiv
The Regulatory Mechanism of Transthyretin Irreversible Aggregation through Liquid-to-Solid Phase Transition.36835140 · Duan, Guangfei, Li, Yanqin, Ye, Meimei et al.2023 · 9 citationsInternational journal of molecular sciences. 2023;24(4)
Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization2210.14567v1 · Hexin Liu, Haihua Xu, Leibny Paola Garcia et al.2022 · 30 citationsarXiv
PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection2210.03221v5 · Shuyue Stella Li, Xiangyu Zhang, Shu Zhou et al.2022 · 0 citationsarXiv
High energy Millihertz quasi-periodic oscillations in 1A 0535+262 with Insight-HXMT challenge current models2209.10455v1 · Ruican Ma, Lian Tao, Shuang-Nan Zhang et al.2022 · 10 citationsarXiv
Engineering Glucose-to-Glycerol Pathway in Klebsiella pneumoniae and Boosting 3-Hydroxypropionic Acid Production Through CRISPR Interference.35845395 · Liu, Hexin, Zhao, Peng, Tian, Pingfang2022 · 10 citationsFrontiers in bioengineering and biotechnology. 2022;10:908431
Quasi-periodic oscillations of the X-ray burst from the magnetar SGR J1935+2154 and associated with the fast radio burst FRB 2004282204.03253v1 · Xiaobo Li, Mingyu Ge, Lin Lin et al.2022 · 46 citationsarXiv
PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification2203.12366v2 · Hexin Liu, Leibny Paola Garcia Perera, Andy W. H. Khong et al.2022 · 13 citationsarXiv
Enhance Language Identification using Dual-mode Model with Knowledge Distillation2203.03218v1 · Hexin Liu, Leibny Paola Garcia Perera, Andy W.H. Khong et al.2022 · 1 citationarXiv
Career total: 99 works. 43 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.