%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:27:34 AM

@INPROCEEDINGS{valente:Interspeech:2007,
         author = {Valente, Fabio and Vepa, Jithendra and Plahl, Christian and Gollan, Christian and Hermansky, Hynek and Schl{\"{u}}ter, Ralf},
       projects = {Idiap},
          title = {Hierarchical Neural Networks Feature Extraction for LVCSR system},
      booktitle = {Interspeech 2007},
           year = {2007},
           note = {IDIAP-RR 07-08},
       crossref = {valente:rr07-08},
       abstract = {This paper investigates the use of a hierarchy of Neural Networks for performing data driven feature extraction. Two different hierarchical structures based on long and short temporal context are considered. Features are tested on two different LVCSR systems for Meetings data (RT05 evaluation data) and for Arabic Broadcast News (BNAT05 evaluation data). The hierarchical NNs outperforms the single NN features consistently on different type of data and tasks and provides significant improvements w.r.t. respective baselines systems. Best result is obtained when different time resolutions are used at different level of the hierarchy.},
            pdf = {https://publications.idiap.ch/attachments/papers/2007/valente-Interspeech-2007.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2007/valente-Interspeech-2007.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{valente:rr07-08,
         author = {Valente, Fabio and Vepa, Jithendra and Plahl, Christian and Gollan, Christian and Hermansky, Hynek and Schl{\"{u}}ter, Ralf},
       projects = {Idiap},
          title = {Hierarchical Neural Networks Feature Extraction for LVCSR system},
           type = {Idiap-RR},
         number = {Idiap-RR-08-2007},
           year = {2007},
    institution = {IDIAP},
           note = {Submitted for publication},
       abstract = {This paper investigates the use of a hierarchy of Neural Networks for performing data driven feature extraction. Two different hierarchical structures based on long and short temporal context are considered. Features are tested on two different LVCSR systems for Meetings data (RT05 evaluation data) and for Arabic Broadcast News (BNAT05 evaluation data). The hierarchical NNs outperforms the single NN features consistently on different type of data and tasks and provides significant improvements w.r.t. respective baselines systems. Best result is obtained when different time resolutions are used at different level of the hierarchy.},
            pdf = {https://publications.idiap.ch/attachments/reports/2007/valente-idiap-rr-07-08.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2007/valente-idiap-rr-07-08.ps.gz},
ipdmembership={speech},
}