Language:
You're in ResearchersJordi Luque

Jordi Luque

Speech Processing, Signal Modeling and Complex Networks

Jordi’s interests are related to the fields of signal processing, time series analysis, machine learning and complex networks mainly devoted to speech applications. My research in Telefonica Digital is focused on the field of affective computing and automatic recognition of speaker's traits through his voice, for instance, by developing algorithms and techniques for detection of emotions in speech or to infer the speaker's personality. My expertise comprises mainly algorithms and techniques focused on person recognition and verification, diarization and tracking in multi-modal environments, speaker and channel variability compensation techniques and machine learning applied to features extracted from speech and image, In my previous position, I was working as a post-doc researcher in the Department of Applied Mathematics and Statistics of E.T.S.I.A., at the Technical University of Madrid (UPM), pursuing research on the analysis of speech properties by applying time series analysis techniques from the field of statistical physics.

Recent Publications:

  • J. Luque, L. Lacasa, B. Luque, "Scaling and universality in the human voice",   [pdf]
  • C. Gracia, X. Anguera, J. Luque and I. Artzi, "Phoneme-Lattice to Phoneme-Sequence matching algorithm based on Dynamic Programming", book chapter in Advances in Speech and Language Technologies for Iberian Languages. Lecture Notes in Computer Science, Volume 8854, 2014, pp. 99-108. Presented at Iberspeech 2014, Las Palmas, Spain. [pdf]                                                                                                                                            
  • M. Ferrarons, X. Anguera and J. Luque, "Flexible Stand-alone Keyword RecognitionApplication using Dynamic Time Warping", book chapter in Advances in Speech and Language Technologies for Iberian Languages. Lecture Notes in Computer Science, Volume 8854, 2014, pp. 158-167. Presented at Iberspeech 2014, Las Palmas, Spain. [pdf]
  • X. Anguera, J. Luque and C. Gracia, "Audio-to-text Alignment for speech recognition with very limited resources",  in Proceedings Interspeech 2014, Singapore [pdf]

  • J. Luque and X. Anguera "On the Modeling of Natural Vocal Emotion Expressions Through Binary Key", in Proceedings Eusipco 2014, Lisboa, Portugal [pdf]                                                                                                     
  • J.C. Pereira, J. Luque, X. Anguera, “Sentiment retrieval on web reviews using spontaneous natural speech“, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’14), May 2014 [pdf]

  • S.H. Yella, X. Anguera, J. Luque, “Inferring social relationships in a phone call from a single party’s speech“, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’14), May 2014 [pdf]

  • X. Anguera, M. Skácel, V. Vorwerk, J. Luque, “The Telefonica Research Spoken Web Search System for MediaEval 2013“, CEUR Workshop Proceedings, 2013 [pdf] 

  •  J. Luque and J. Hernando,“On the use of Agglomerative and Spectral Clustering in Speaker Diarization of Meetings“ in Proceedings Odyssey’12, The Speaker and Language Recognition Workshop 2012, September 2012

  • M. Zelenák, C. Segura , J. Luque , J. Hernando, ”Simultaneous Speech Detection With Spatial Features for Speaker Diarization,” IEEE Transactions on Audio, Speech, and Language Processing, vol.20, no.2, pp.436-446, Feb. 2012

  •  J. Luque, L. Lacasa, B. Luque, “Power Laws and Scaling in the Waiting Time Distribution of Speech ”, XVIII Congreso de Física Estadística“, FisEs’12, Palma, Mallorca. October 2012

  • E. Bonet-Carne, T. Cobo, J. Luque, M. Martínez-Terrón, A. Perez-Moreno, M. Palacio, E. Gratacos, I. Amat-Roldan, “Consistent Association Between Image Features of Fetal Lungs from Different Ultrasound Equipments and Fetal Lung Maturity from Amniocentesi”, IEEE International Symposium on Biomedical Imaging (ISBI’12), 2012

  • A. Abad, J. Luque, I. Trancoso, “Parallel Transformation Network features for Speaker Recognition“, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP’11), May 2011

  • M. Sanz-Cortés, F. Figueras, N. Padilla, N. Bargalló, E. Bonet, J. Luque, I. Amat, E. Gratacós, ”Evaluation of a computer-based analysis of brain textures on fetal MRI to detect changes in small for gestational age (SGA) fetuses and to predict neurodevelopmental outcome“, ISUOG’11 World Congress, International Society of Ultrasound in Obstetrics and Gynecology, 2011

  • A. Abad and J. Luque, “Connectionist Transformation Network Features for Speaker Recognition“, Proceedings Odyssey’10, The Speaker and Language Recognition Workshop 2010, pp. 5300-5303, 2010

  • B. Luque, L. Lacasa, F. Ballesteros and J. Luque “Horizontal visibility graphs: Exact results for random time series“, Physical Review E, PRE, vol. 80, Issue 4, id. 046103, 2009

  • L. Lacasa, B. Luque, J. Luque, J. C. Nuño. “The visibility graph: A new method for estimating the Hurst exponent of fractional Brownian motion“, Journal on Europhysics Letters, EPL, vol. 86, pp. 30001, 2009

  • J. Luque, C. Segura, J. Hernando,“Clustering initialization based on spatial information for speaker diarization of meetings“, Proceedings International Conference on Spoken Language Processing (ICSLP’08), pp. 383-386, 2008

  • L. Lacasa, B. Luque, F. Ballesteros, J. Luque, J.C. Nuño, “From time series to complex networks: The visibility graph“, Proceedings of the National Academy of Science of the USA, PNAS, vol. 105, no. 13, pp. 4972-4975, 2008

     

Patents:

  • J. Neystad, M. Asadurian, J. Luque, X. Anguera, Patent disclosure, P-1300028 “Online keyword spotting & emotion recognition”, 2013

     

     

Jordi Luque's publications:


    - 2014:

    1. "Sentiment retrieval on web reviews using spontaneous natural speech ", Jose Costa Pereira , Jordi Luque , Xavier Anguera .
      IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 14
    1. "Inferring social relationships in a phone call from a single party’s speech ", Sree Harsha Yella , Xavier Anguera , Jordi Luque .
      IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 14