Guodong Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Guodong Liu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Guihai Chen
Shanghai Jiao Tong University
2 shared publications - Haipeng Dai
Nanjing University
2 shared publications - Lei Wang
Soochow University, Suzhou, China
2 shared publications - Qianran Qiao
Nanjing University, Nanjing, China
2 shared publications - Yun Bo Li
State Key Laboratory of Millimeter Waves, Southeast University, Nanjing, China
2 shared publications - Cheng Peng
Soochow University, Suzhou, China
1 shared publication
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1463-1478
General Speech Reconstruction for Voice Calls Using Smartphone's Built-in Accelerometer
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1463-1478
Open AccessGeneral Speech Reconstruction for Voice Calls Using Smartphone's Built-in Accelerometer
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (1) , 1-28
LAM-assisted Acoustic Eavesdropping in Multi-speaker Scenarios via Commercial mmWave Radar
Eavesdropping on target speech in enclosed and private rooms, such as secret gatherings or private parties, has become a growing research trend and poses one of the most significant threats to personal privacy leakage. Previous studies often made various assumptions about the target and scenarios of eavesdropping, such as the presence of only a single speaker, a very slow speech rate, and clear separation of words, all of which greatly limited the applicability of eavesdropping systems. In this paper, we propose an acoustic eavesdropping system, mmMPS, based on commercial off-the-shelf millimeter-wave (COTS mmWave) radar, which is capable of eavesdropping on specific target speech in scenarios where multiple people speak simultaneously, without requiring prior knowledge of background voices, speech rate, or intensity. The system utilizes a single COTS mmWave radar to capture faint signals caused by the vibration of objects due to human speech, combines these with our proposed denoising algorithm to recover the speech signal, and then uses our recognition model along with large audio model (LAM) to extract target keyword speech from the mixed speech signals of multiple speakers. Extensive experiments were conducted on a nearly 120 hours audio dataset and 60 hours radar dataset that we created using LAM and collected in experimental scenarios. The system is capable of covering various target users, speech rates, and speech intensities. The results show that in a scenario with 1–2 simultaneous speakers, the system achieves the average WER/CER (Word/Character Error Rate) of 6.46% (the lower, the better) in identifying 36 target keywords. In a scenario of 3–5 speakers, the average WER/CER is 14.97%, and even in the scenario with up to 7 simultaneous speakers, the average WER/CER remains below 30%. To the best of our knowledge, mmMPS is the first system to achieve high-accuracy eavesdropping on target speech in multi-speaker scenarios, significantly expanding the application scope of acoustic eavesdropping.
- 16 March 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (1) , 1-28
Open AccessLAM-assisted Acoustic Eavesdropping in Multi-speaker Scenarios via Commercial mmWave Radar
Eavesdropping on target speech in enclosed and private rooms, such as secret gatherings or private parties, has become a growing research trend and poses one of the most significant threats to personal privacy leakage. Previous studies often made various assumptions about the target and scenarios of eavesdropping, such as the presence of only a single speaker, a very slow speech rate, and clear separation of words, all of which greatly limited the applicability of eavesdropping systems. In this paper, we propose an acoustic eavesdropping system, mmMPS, based on commercial off-the-shelf millimeter-wave (COTS mmWave) radar, which is capable of eavesdropping on specific target speech in scenarios where multiple people speak simultaneously, without requiring prior knowledge of background voices, speech rate, or intensity. The system utilizes a single COTS mmWave radar to capture faint signals caused by the vibration of objects due to human speech, combines these with our proposed denoising algorithm to recover the speech signal, and then uses our recognition model along with large audio model (LAM) to extract target keyword speech from the mixed speech signals of multiple speakers. Extensive experiments were conducted on a nearly 120 hours audio dataset and 60 hours radar dataset that we created using LAM and collected in experimental scenarios. The system is capable of covering various target users, speech rates, and speech intensities. The results show that in a scenario with 1–2 simultaneous speakers, the system achieves the average WER/CER (Word/Character Error Rate) of 6.46% (the lower, the better) in identifying 36 target keywords. In a scenario of 3–5 speakers, the average WER/CER is 14.97%, and even in the scenario with up to 7 simultaneous speakers, the average WER/CER remains below 30%. To the best of our knowledge, mmMPS is the first system to achieve high-accuracy eavesdropping on target speech in multi-speaker scenarios, significantly expanding the application scope of acoustic eavesdropping.
- 17 September 2023
- Published by Wiley in Advanced Materials Technologies
- Vol. 8 (22)
Indoor Positioning and Posture Recognition of Human Body Applying Integrating‐Type Intelligent Metasurfaces Based Sensing System
The electromagnetic (EM) detection and sensing research of human signs are becoming much more attractive, especially with the rise of intelligent metasurface which can strongly enhance the control abilities and functionalities of transmitting and receiving EM fields. It proposes the design of integrating‐type intelligent metasurface to realize the indoor positioning and posture recognition of the human body using the support vector machine algorithm and a new deep learning algorithm model it proposed called MetaNet. The integrating‐type metasurface with the in‐plane feed rather than horn excitation is real low profile, and the varactor based programmable phase shifters achieving 360‐degree cover and continuous control of phase are independently embedded in each unit cell for further synthesized manipulation of apertures. One pair of integrating‐type intelligent metasurfaces are fabricated for transmitting and receiving EM fields, respectively. Also, the corresponding prototype of radar transceiver system is developed and manufactured to rapidly acquire massive data. The total experimental flow can include two main steps that first, the transmitting and receiving beams of metasurfaces should scan dynamically and synchronously under the method of far‐field synthesis for detecting the direction of the human. Second, the transmitting beam should keep the detected direction and the receiving apertures of metasurface should be varied by randomly control the phase shift of each unit cell for multiple sensing. Based on the technology of deep learning to process the massive receiving data, the profile images and key points of various human postures can be reconstructed very well in the measurement that can verify the validity of the proposed sensing system.
- 17 September 2023
- Published by Wiley in Advanced Materials Technologies
- Vol. 8 (22)
Indoor Positioning and Posture Recognition of Human Body Applying Integrating‐Type Intelligent Metasurfaces Based Sensing System
The electromagnetic (EM) detection and sensing research of human signs are becoming much more attractive, especially with the rise of intelligent metasurface which can strongly enhance the control abilities and functionalities of transmitting and receiving EM fields. It proposes the design of integrating‐type intelligent metasurface to realize the indoor positioning and posture recognition of the human body using the support vector machine algorithm and a new deep learning algorithm model it proposed called MetaNet. The integrating‐type metasurface with the in‐plane feed rather than horn excitation is real low profile, and the varactor based programmable phase shifters achieving 360‐degree cover and continuous control of phase are independently embedded in each unit cell for further synthesized manipulation of apertures. One pair of integrating‐type intelligent metasurfaces are fabricated for transmitting and receiving EM fields, respectively. Also, the corresponding prototype of radar transceiver system is developed and manufactured to rapidly acquire massive data. The total experimental flow can include two main steps that first, the transmitting and receiving beams of metasurfaces should scan dynamically and synchronously under the method of far‐field synthesis for detecting the direction of the human. Second, the transmitting beam should keep the detected direction and the receiving apertures of metasurface should be varied by randomly control the phase shift of each unit cell for multiple sensing. Based on the technology of deep learning to process the massive receiving data, the profile images and key points of various human postures can be reconstructed very well in the measurement that can verify the validity of the proposed sensing system.
- 16 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (10) , 8061-8071
Joint Detections of Frequency and Direction of Arrival in Wideband Based on a Programmable Metasurface
We propose a novel approach for achieving joint detections of frequency and direction of arrival in wideband using single sensor based on an active metasurface with programmable transmission states of pass and stop. By integrating two PIN diodes with the opposite directions into the proposed single-layer and ultrathin meta-atom, the transmission performance with 10 dB difference between the pass and stop states is realized in the bandwidth from 5.9 GHz to 8.8 GHz using field-circuit co-simulations. Accordingly, random receiving patterns are generated by controlling the programmable metasurface composed of the switchable meta-atoms. Afterwards, the frequency and direction information of sources located in the far field are detected using the modified algorithm of estimating signal parameters via rotational invariance techniques (ESPRIT) and the compressive sensing method, respectively. A sample of the programmable metasurface is fabricated and the voltage control system is built up correspondingly. To verify the proposed method’s validity, we conduct three typical categories of experiments: single-source, double sources with different frequencies, and double sources with the same frequency. In all cases, the source information of frequency and direction has been detected preciously in measurements within the frequency band from 6.2 GHz to 8.8 GHz.
- 16 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 71 (10) , 8061-8071
Joint Detections of Frequency and Direction of Arrival in Wideband Based on a Programmable Metasurface
We propose a novel approach for achieving joint detections of frequency and direction of arrival in wideband using single sensor based on an active metasurface with programmable transmission states of pass and stop. By integrating two PIN diodes with the opposite directions into the proposed single-layer and ultrathin meta-atom, the transmission performance with 10 dB difference between the pass and stop states is realized in the bandwidth from 5.9 GHz to 8.8 GHz using field-circuit co-simulations. Accordingly, random receiving patterns are generated by controlling the programmable metasurface composed of the switchable meta-atoms. Afterwards, the frequency and direction information of sources located in the far field are detected using the modified algorithm of estimating signal parameters via rotational invariance techniques (ESPRIT) and the compressive sensing method, respectively. A sample of the programmable metasurface is fabricated and the voltage control system is built up correspondingly. To verify the proposed method’s validity, we conduct three typical categories of experiments: single-source, double sources with different frequencies, and double sources with the same frequency. In all cases, the source information of frequency and direction has been detected preciously in measurements within the frequency band from 6.2 GHz to 8.8 GHz.