You are here

jalalvand

  • SKYPE: shahabkhaan
  • Phone: +39 +39 0461 314549
  • FBK Povo
Short bio

Shahab is currently a PhD student in the University of Trento and he is a member of Human Language Technology group at FBK research center. Shahab was born in Tehran, IRAN (1985). He recieved his B.Sc. (2009) and M.Sc. (2012) in the field of computer engineering and artificial intelligence from Iran University of Science and Technology. For the M.Sc. Degree, he did his research on speech processing and pattern recognition. Accent classification and acoustic model adaptation for American English accents and Persian accents were his major topics. Currently he is working on Neural Network Language Modeling and the methods of using these complex LMs for improving the ASR results.

Research interests
Speech Recognition Language Modeling Deep Learning Pattern Recognition
Personal documents
Publications

2015

  • Shahab Jalalvand, Daniele Falavigna, Marco Matassoni, Piergiorgio Svaizer, and Maurizio Omologo. “Boosted Acoustic Model Learning and Hypotheses Rescoring on the CHiME3 Task”. In: (TO BE APPEARED) in The 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Arizona, USA. 
  • Shahab Jalalvand, "Stacked Auto-Encoder for ASR Error Detection and Word Error Rate Prediction", In INTERSPEECH2015, Dresden, Germany, 2015. (.pdf)
  • Shahab Jalalvand, Matteo Negri, Daniele Falavigna and Marco Turchi, "Driving ROVER with Segment-based ASR Quality Estimation", In ACL2015, Beijing, China, 2015. (.pdf

2014

  • Bagher Babaali, Romain Serizel, Shahab Jalalvand, Daniele Falavigna, Roberto Gretter, and Diego Giuliani. “FBK@ IWSLT 2014-ASR track”. In: Proc. of the International Workshop on Spoken Language Translation. Lake Tahoe, California, USA, pp. 18–25. (.pdf)
  • Shahab Jalalvand and Daniele Falavigna, "Direct Word Graph Rescoring using A* Search and RNNLM", In INTERSPEECH2014, Singapore, 2014. (.pdf)

2013

  • Shahab Jalalvand and Daniele Falavigna, "Parameter Optimization for Iterative Confusion Network Decoding in Weather-Domain Speech Recognition", In IWSLT2013, Heidelberg, Germany, pp. 333-337, Dec. 05-06, 2013. (.pdf)
  • Alexei V. Ivanov, Shahab Jalalvand, Roberto Gretter, Daniele Falavigna, "Phonetic and anthropometric conditioning of MSA-KST cognitive impairment characterization system". In ASRU2013, Olomouc, Czech Republic, pp. 228-233, Dec 08-12, 2013. (.pdf)
  • Shahab Jalalvand, "Improving Language Model Adaptation using Automatic Data Selection and Neural Network", In RANLP 2013, pp 86-92, Hissar, Bulgaria, Sep. 09-11, 2013. (.pdf)

2012

  • Shahab Jalalvand, Ahmad Akbari, Babak Nasersharif, "A Classifier Combination Approach for Farsi Accents Recognition”, In ICEE2012, pp. 716-720, Tehran, Iran, May. 15-17, 2012 (Best Presentation Award) (.pdf)