Return to Members

Xiaofei LI


I work in the PERCEPTION team at INRIA Grenoble Rhône-Alpes as a  post-doctoral researcher from February 2014 to January 2016, and as a starting research scientist since February 2016.  I was involved in the EARS project, ERC VHIA project and  Samsung Electronics Lito project of PERCEPTION team. My research interests include multi-microphone speech processing for sound source localization, separation and dereverberation, single microphone signal processing for noise estimation, voice activity detection, and speech enhancement.

I received a Bachelor degree in Electronic Information from Beijing Institute of Machinery, China in 2007. I did my PhD in Electronics at Peking University, China during 2007 to 2013.

 


Contact

  • INRIA Grenoble Rhone-Alpes
    655, avenue de l’Europe
    38330 Montbonnot Saint-Martin
    France
  • Email: xiaofei dot li at inria dot fr

Publications

GoogleScholar

2019

  • Online Localization and Tracking of Multiple Moving Speakers in Reverberant Environments [pdf] [research page] [matlab code]
    Xiaofei Li, Yutong Ban, Laurent Girin, Xavier Alameda-Pineda, Radu Horaud
    IEEE Journal of Selected Topics in Signal Processing, 13 (1), pp. 88 – 103, 2019.
  • Multichannel Speech Separation and Enhancement Using the Convolutive Transfer Function [pdf] [matlab code]
    Xiaofei Li, Laurent Girin, Sharon Gannot, Radu Horaud
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 27 (3), pp. 645 – 659, 2019.
  • Audio-noise Power Spectral Density Estimation Using Long Short-term Memory [pdf]
    Xiaofei Li, Simon Leglaive, Laurent Girin, Radu Horaud
    IEEE Signal Processing Letters, 2019.
  • Expectation-Maximization for Speech Source Separation using Convolutive Transfer Function [pdf] [matlab code]
    Xiaofei Li, Laurent Girin, Radu Horaud
    CAAI Transactions on Intelligent Technologies, 4 (1), pp. 47 – 53, 2019.
  • Multiple Sound Source Counting and Localization Based on TF-Wise Spatial Spectrum Clustering
    Bing Yang, Hong Liu, Cheng Pang, Xiaofei Li
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019.
  • Multitask Learning of Time-Frequency CNN for Sound Source Localization [pdf]
    Cheng Pang, Hong Liu, Xiaofei Li
    IEEE Access, vol.7, pp. 40725 – 40737, 2019.

2018

  • Audio source separation into the wild [pdf]
    Laurent Girin, Sharon Gannot, Xiaofei Li
    Multimodal Behavior Analysis in the Wild, Academic Press (Elsevier), Computer Vision and Pattern Recognition, 〈10.1016/B978-0-12-814601-9.00022-5〉, pp. 53-78, 2018.
  • Multichannel Identification and Nonnegative Equalization for Dereverberation and Noise Reduction based on Convolutive Transfer Function [pdf] [audio examples] [matlab code]
    Xiaofei Li, Sharon Gannot, Laurent Girin, Radu Horaud
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 26 (10), pp. 1755 – 1768, 2018.
  • Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion [research page]
    Israel D. Gebru, Silèye Ba, Xiaofei Li, Radu Horaud
    IEEE Transactions on pattern analysis and machine intelligence, 40 (5), pp. 1086 – 1099, 2018.
  • Online Localization of Multiple Moving Speakers in Reverberant Environments [pdf] [matlab code]
    Xiaofei Li, Bastien Mourgue, Laurent Girin, Sharon Gannot and Radu Horaud
    IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM), July 2018, Sheffield, UK.
  • Multisource MINT Using the Convolutive Transfer Function [pdf] [matlab code]
    Xiaofei Li, Sharon Gannot, Laurent Girin, Radu Horaud
    IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), Apr 2018, Calgary, Canada.
  • A Cascaded Multiple-Speaker Localization and Tracking System [pdf] [research page] [matlab code]
    Xiaofei Li, Yutong Ban, Laurent Girin, Xavier Alameda-Pineda, Radu Horaud
    Proceedings of the LOCATA Challenge Workshop – a satellite event of IWAENC 2018, Sep 2018, Tokyo, Japan. pp.1-5.
  • Accounting for Room Acoustics in Audio-Visual Multi-Speaker Tracking
    Yutong Ban, Xiaofei Li, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud
    IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP), Apr 2018, Calgary, Canada.

2017

  • Multiple-Speaker Localization Based on Direct-Path Features and Likelihood Maximization with Spatial Sparsity Regularization [pdf] [research page]
    Xiaofei Li, Laurent Girin, Radu Horaud and Sharon Gannot
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 25 (10), pp. 1997 – 2012, 2017.
  • Binaural Sound Localization Based on Reverberation Weighting and Generalized Parametric Mapping
    Cheng Pang, Hong Liu, Jie Zhang and Xiaofei Li
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 25 (8), pp. 1618 – 1632, 2017.
  • An EM algorithm for audio source separation based on the convolutive transfer function [pdf] [matlab code]
    Xiaofei Li, Laurent Girin, Radu Horaud
    IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Oct 2017, New Paltz, NY, United States.
  • Audio Source Separation based on Convolutive Transfer Function and Frequency-Domain Lasso Optimization [pdf ]
    Xiaofei Li, Laurent Girin, Radu Horaud
    IEEE International Conference on Audio, Speech and Signal Processing (ICASSP), Mar 2017, New Orleans, United States.

2016

  • Estimation of the Direct-Path Relative Transfer Function for Supervised Sound-Source Localization [pdf] [matlab code] [research page]
    Xiaofei Li, Laurent Girin, Radu Horaud, Sharon Gannot
    IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016, 24 (11), pp. 2171 – 2186.
  • A Novel Lip Descriptor for Audio-Visual Keyword Spotting Based on Adaptive Decision Fusion [pdf]
    Pingping Wu, Hong Liu, Xiaofei Li, Ting Fan, Xuewu Zhang
    IEEE Transactions on Multimedia 18(3), pp. 326-338, 2016.
  • Reverberant Sound Localization with a Robot Head Based on Direct-Path Relative Transfer Function [pdf]
    Xiaofei Li, Laurent Girin, Fabien Badeig, Radu Horaud
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct 2016, Daejeon, South Korea.
  • Voice Activity Detection Based on Statistical Likelihood Ratio With Adaptive Thresholding [pdf]
    Xiaofei Li, Radu Horaud, Laurent Girin, Sharon Gannot
    International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2016, Xi’an, China.
  • Non-Stationary Noise Power Spectral Density Estimation Based on Regional Statistics [pdf] [matlab code]
    Xiaofei Li, Laurent Girin, Sharon Gannot, Radu Horaud
    IEEE International Conference on Audio, Speech and Signal Processing (ICASSP), Mar 2016, Shangai, China.

2015

  • A Distributed Architecture for Interacting with NAO [pdf]
    Fabien Badeig, Quentin Pelorson, Soraya Arias, Vincent Drouard, Israel Dejene Gebru, Xiaofei Li, Georgios Evangelidis, Radu Horaud
    International Conference on Multimodal Interaction (ICMI), Nov 2015, Seattle, WA, United States.
  • Local Relative Transfer Function for Sound Source Localization [pdf]
    Xiaofei Li, Radu Horaud, Laurent Girin, Sharon Gannot
    The European Signal Processing Conference (Eusipco), Aug 2015, Nice, France.
  • Estimation of Relative Transfer Function in the Presence of Stationary Noise Based on Segmental Power Spectral Density Matrix Subtraction [pdf] [matlab code]
    Xiaofei Li, Laurent Girin, Radu Horaud, Sharon Gannot
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia.

Before 2015

  • Sound Source Localization for HRI Using FOC-based Time Difference Feature and Spatial Grid Matching [pdf]
    Xiaofei Li and Hong Liu
    IEEE Transactions on Cybernetics, 43 (4), pp. 1199-1212, 2013
  • Real-time Sound Source Localization for Mobile Robot Based on Guided Spectral-Temporal Position Method [pdf]
    Xiaofei Li, Miao Shen, Wenmin Wang and Hong Liu
    International Journal of Advanced Robotic Systems, 2012, vol.9, 78:2012
  • A survey of sound source localization for robot audition
    Xiaofei Li and Hong Liu
    CAAI Transactions on Intelligent Systems, 7 (1), pp. 9-20, 2012. (in Chinese)
  • A Two-Layer Probabilistic Model Based on Time-Delay Compensation for Binaural Sound Localization [pdf]
    Hong Liu, Zhuo Fu and Xiaofei Li
    IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany, 6-10, May, 2013
  • Time Delay Estimation for Speech Signal Based on FOC-Spectrum [pdf]
    Hong Liu and Xiaofei Li
    International Conference on INTERSPEECH, Portland, Oregon, USA, 2012:1732-1735
  • Sound Source Localization for Human-Robot Interaction Based on Spatial Distribution of Time Difference Feature and Grid Matching [pdf]
    Xiaofei Li, Hong Liu and Xuesong Yang
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2011.
  • A Selection Method of Speech Vocabulary for Human-Robot Speech Interaction [pdf]
    Hong Liu and Xiaofei Li
    IEEE International Conference on Systems, Man and Cybernetics (SMC), Istanbul, Turkey, 2010:2243-2248