logo Idiap Research Institute        
 [BibTeX] [Marc21]
Hierarchical Neural Networks Feature Extraction for LVCSR system
Type of publication: Idiap-RR
Citation: valente:rr07-08
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.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors Valente, Fabio
Vepa, Jithendra
Plahl, Christian
Gollan, Christian
Hermansky, Hynek
Schlüter, Ralf
Crossref by valente:Interspeech:2007
Added by: [UNK]
Total mark: 0
Attachments
  • valente-idiap-rr-07-08.pdf
  • valente-idiap-rr-07-08.ps.gz
Notes