Publications

Doctoral Thesis:

• Jun Qi, "Theoretical Error Performance Analysis for Deep Neural Network Based Regression Functional Approximation," Georgia Institute of Technology

Book Chapter:

• Jun Qi, "Federated Quantum Natural Gradient Descent for Quantum Federated Learning," In Pin-Yu Chen and Lam M. Nguyen, editors, Federated Learning (pp. 329-341). Academic Press, 2024

Preprint Papers:

Quantum Machine Learning

• Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hsiu Hsieh, "Pre-Training Tensor-Train Networks Facilitates Machine Learning with Variational Quantum Circuits," arXiv:2306.03741, in Submission

Journal Papers: (*corresponding authors)

Quantum Machine Learning

• Jun Qi*, Chao-Han Huck Yang, Pin-Yu Chen*, Min-Hsiu Hsieh*, "Theoretical Error Performance Analysis for Variational Quantum Circuit Based Functional Regression," npj Quantum Information, Nature Publishing Group UK London,  Vol. 9, no. 4, 2023 (Impact Factor: 10.89)

• Jun Qi*, Chao-Han Huck Yang, Pin-Yu Chen, "QTN-VQC: An End-to-End Learning Framework for Quantum Neural Networks," Physica Scripta, Vol. 99, no. 1, pp. 015111, 2023 (previously reported in NeurIPS workshop in 2021)

• Yeh-Chi Chen, Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, Hsi-Sheng Goan, “Variational Quantum Circuits for Deep Reinforcement Learning,” IEEE Access, Vol. 8, pp. 141007-141024, 2020

Speech, Language, and Signal Processing

• Jiadi Yao, Hong Luo, Jun Qi, Xiao-Lei Zhang, "Interpretable Spectrum Transformation Attacks to Speaker Recognition Systems," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 32, pp. 1531-1545, 2024

• Jun Qi*, Chao-Han Huck Yang, Pin-Yu Chen, Javier Tejedor, "Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent with Illustration of Speech Processing," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 31, pp. 633-642, 2023

• Muhammad Omar, Jun Qi, Xiaoli Ma, "Mitigating Clipping Distortion in Multicarrier Transmissions Using Tensor-Train Deep Neural Networks," IEEE Transactions on Wireless Communications, pp. 2127-2138, Vol. 22, no. 3, 2022

• Jing Zhang, Xiaoli Ma, Jun Qi, Shi Jin, "Tensor-Train Deep Neural Network Based Channel Estimation Over Time-Varying MIMO Channels," IEEE Journal of Selected Topics in Signal Processing, 15, no. 3, pp. 759-773, 2021

• Jun Qi*, Jun Du, Sabato Marco Siniscalchi, Xiaoli Ma, Chin-Hui Lee, "Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression," IEEE Transactions on Signal Processing, Vol 68, pp. 3411-3422, 2020

• Jun Qi*, Jun Du, Sabato Marco Siniscalchi, Xiaoli Ma, Chin-Hui Lee, “On Mean Absolute Error for Deep Neural Network-based Vector-to-Vector Regression,” IEEE Signal Processing Letters, Vol. 27, pp. 1485-1489, 2020

• Jun Qi*, Jun Du, Sabato Marco Siniscalchi, Chin-Hui Lee, "A Theory on Deep Neural Network-based Vector-to-Vector Regression with an Illustration of Its Expressive Power in Speech Enhancement," IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol 27,  no. 12, pp. 1932-1943, 2019

Conference Papers:

Quantum Natural Language Processing

• Jun Qi, Xiao-Lei Zhang, Javier Tejedor, "Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent," IEEE Intl. Conf. on Acoustic, Speech, and Signal Processing (ICASSP), 2023

• Jun Qi, Javier Tejedor, "Classical-to-Quantum Transfer Learning for Spoken Command Recognition based on Quantum Neural Networks," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2022

• Chao-Han Huck Yang, Jun Qi, Yen-Chi Chen, Yu Tsao, Pin-Yu Chen, "When BERT Meets Quantum Temporal Convolutional Learning for Text Classification in Heterogeneous Computing," IEEE Intl. Conf. Acoustic, Speech, and Signal Processing (ICASSP), 2022

• Chao-Han Huck Yang, Jun Qi, Yen-Chi Chen, Pin-Yu Chen, Sabato Marco Siniscalchi, Xiaoli Ma, Chin-Hui Lee, "Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech Recognition,"  IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2021

Speech, Language, and Signal Processing

• Jun Qi, Javier Tejedor, "Exploiting Hybrid Models of Tensor-Train Networks for Spoken Command Recognition," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2022

• Jun Qi, Hu Hu, Yannan Wang, Chao-Han Huck Yang, Sabato Marco Siniscalchi, Chin-Hui Lee, "Tensor-to-Vector Regression for Multi-Channel Speech Enhancement based on Tensor-Train Network,” IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2020 

• Jun Qi, Chao-Han Huck Yang, Javier Tejedor, “Submodular Rank Aggregation for Score-based Permutations for Distributed Automatic Speech Recognition,” IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2020

• Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, Chin-Hui Lee, “Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement,” IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2020

• Jun Qi, Hu Hu, Chao-Han Huck Yang, Sabato Marco Siniscalchi, Chin-Hui Lee, “Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression-based Speech Enhancement,” Annual Conference of the International Speech Communication Association (INTERSPEECH), 2020

• Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, "Enhanced Adversarial Strategically-Timed Attacks on Deep Reinforcement Learning," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2020

• Jun Qi, Xu Liu, Shunsuke Kamijo, Javier Tejedor, "Distributed Submodular Maximization for Large-scale Vocabulary Continuous Speech Recognition," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2018

• Jun Qi, Javier Tejedor, “Robust Submodular Data Partitioning for Distributed Speech Recognition," IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2016

• Jun Qi, Javier Tejedor, “Deep Multi-View Representation Learning for Multi-modal Features of the Schizophrenia and Schizo-affective Disorder,” IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 2016

• Jun Qi, Dong Wang, Ji Xu, Javier Tejedor, “Bottleneck Features based on Gamma-tone Frequency Cepstral Coefficients,” Annual Conference of the International Speech Communication Association (INTERSPEECH), 2013.

• Jun Qi, Dong Wang, Javier Tejedor, “Subspace Models for Bottleneck Features,” Annual Conference of the International Speech Communication Association (INTERSPEECH), 2013. 

• Jun Qi, Dong Wang, Yi Jiang, Runsheng Liu, “Auditory Features based on Gammatone Filters for Robust Speech Recognition,” IEEE International Symposium on Circuits and Systems (ISCAS), 2013.