You are here

Diego Giuliani

  • SKYPE: diego.tn.it
  • Phone: +39 0461314556
  • FBK Povo
Short bio

I received a Laurea degree in Computer Science from the University of Milan in 1986. In 1988, I joined ITC-irst, now Bruno Kessler Foundation (FBK). During 1989 I was a Visiting Researcher at McGill University, Montreal, Canada. Since then I have been doing research in automatic speech recognition with particular interest in acoustic modeling, large-vocabulary speech recognition, speaker adaptation, microphone arrays, children's speech recognition and artificial neural networks. I have been involved in several EU funded projects: SPEEDATA (1995-1998), CoreTex (2000-2003), ECHO (2002-2004), PF-STAR (2002-2004), TC-STAR (2004-2007), Jumas (2008-2010), TOSCA-MP (2011-2014) and EU-BRIDGE (2012-2015).

Research interests
Large vocabulary automatic speech recognition; speaker adaptation/normalization; robust speech recognition; acoustic modeling and children's speech recognition
Publications

(Papers are listed in reverse chronological order)

  1. Serizel, Romain; Giuliani, Diego,
    in «NATURAL LANGUAGE ENGINEERING»,
    2016
    , pp. 1 -
    26
  2. Sprugnoli, Rachele; Moretti, Giovanni; Bentivogli, Luisa; Giuliani, Diego,
    Creating a ground truth multilingual dataset of news and talk show transcriptions through crowdsourcing,
    in «LANGUAGE RESOURCES AND EVALUATION»,
    2016
  3. Matassoni, Marco; Falavigna, Giuseppe Daniele; Giuliani, Diego,
    2016 IEEE Workshop on Spoken Language Technology,
    2016
    , (2016 IEEE Workshop on Spoken Language Technology,
    San Diego, California,
    13–16 December 2016)
  4. Diego Giuliani, Bagher BabaAli,
    Proceedings of Interspeech 2015,
    ISCA,
    2015
    , pp. 1635-
    1639
    , (INTERSPEECH 2015,
    Dresden, Germany,
    September, 2015)
  5. Serizel R.; Giuliani D.,
    Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition,
    Proceedings of the IEEE Workshop on Spoken Language Technology,
    2014
    , (IEEE Spoken Language Technology Workshop,
    South Lake Tahoe, California and Nevada,
    Dec 7-10, 2014)
  6. Serizel R.; Giuliani D.,
    Deep neural network adaptation for children's and adults' speech recognition,
    Proceedings of the First Italian Conference on Computational Linguistics,
    2014
    , (Italian Conference on Computational Linguistics,
    Pisa, Italy,
    9-10 December 2014)
  7. BabaAli B.; Serizel R.; Jalalvand S.; Gretter R.; Falavigna D.; Giuliani D.,
    FBK @ IWSLT 2014 - ASR track,
    International Workshop on Spoken Language Translation (IWSLT2014),
    2014
    , (International Workshop on Spoken Language Translation (IWSLT2014),
    Lake Tahoe, USA,
    Dec. 04-05, 2014)
  8. Sprugnoli R.; Moretti G.; Fuoli M.; Giuliani D.; Bentivogli L.; Pianta E.; Gretter R.; Brugnara F.,
    Comparing two methods for crowdsourcing speech transcription,
    Proceedings of ICASSP 2013,
    The Institute of Electrical and Electronics Engineers,Incorporated,
    2013
    , pp. 8116-
    8120
    , (38th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
    Vancouver, CA,
    26-31 May, 2013)
  9. Giuliani D.; Brugnara F.,
    An on-line incremental speaker adaptation technique
    for audio stream transcription
    ,
    Proceedings of Interspeech 2013,
    2013
    , (14th Annual Conference of the International Speech Communication Association,
    Lyon, France,
    25-29 August 2013)
  10. Falavigna G.; Gretter R.; Brugnara F.; Giuliani D.; Serizel H. R.,
    FBK @ IWSLT 2013 - ASR tracks,
    Proceedings of IWSLT2013,
    2013
    Heidelberg (Germany),
    5-6 December 2013)

Pages