HMM/Neural Network-Based System for Italian Conituous Digit Recognition (Contributo in atti di convegno)

Type
Label
  • HMM/Neural Network-Based System for Italian Conituous Digit Recognition (Contributo in atti di convegno) (literal)
Anno
  • 1999-01-01T00:00:00+01:00 (literal)
Alternative label
  • Cosi P., Hosom J.P. (1999)
    HMM/Neural Network-Based System for Italian Conituous Digit Recognition
    in ICPhS-99 - XIV International Congress of Phonetic Sciences, San Francisco, California, USA, 14-18 August, 1999
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Cosi P., Hosom J.P. (literal)
Pagina inizio
  • 1669 (literal)
Pagina fine
  • 1672 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#altreInformazioni
  • Cosi P., Hosom J.P. \"HMM/Neural Network-Based System for Italian Conituous Digit Recognition\" Proceedings XIV International Congress of Phonetic Sciences, ICPhS-99 San Francisco, California, USA 14-18 August, 1999 pp. 1669-1672 http://www2.pd.istc.cnr.it/Papers/PieroCosi/cp-ICPhS99.pdf (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url
  • http://www2.pd.istc.cnr.it/Papers/PieroCosi/cp-ICPhS99.pdf (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume
  • Proceedings of ICPhS-99 - XIV International Congress of Phonetic Sciences (literal)
Note
  • G (literal)
  • CiteSeerX (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • ISTC CNR, UOS Padova Cosi P. Center for Spoken Language Understanding, Oregon Graduate Institute of Science and Technology P.O. Box 91000, Portland Oregon 97291-1000 USA Hosom J.P. (literal)
Titolo
  • HMM/Neural Network-Based System for Italian Conituous Digit Recognition (literal)
Abstract
  • An Italian speaker-independent continuous-speech digit recognizer is described. The CSLU Toolkit was used to develop and implement the system. In the first set of experiments, the SPK-IRST corpus, a collection of digit sentences recorded in a clean environment, was used both for training and testing the system. In the second set, a band-filtered version (between 300 Hz and 3400 Hz) of the SPK-IRST corpus was considered for training, while the telephone PANDA-CSELT corpus was used for testing the system. A hybrid HMM/NN architecture was applied; in this architecture, a three-layer neural network is used as a state emission probability estimator and the conventional forward-backward algorithm is applied for estimating continuous targets for the NN training patterns. The final network, trained to estimate the probability of 116 contextdependent phonetic categories at every 10-msec frame, was not trained on binary target values, but on the probabilities of each phonetic category belonging to each frame. Training and testing will be described in detail and recognition results will be illustrated. (literal)
Editore
Prodotto di
Autore CNR

Incoming links:


Autore CNR di
Prodotto
Editore di
data.CNR.it