Full metadata record
DC FieldValueLanguage
dc.contributor.authorHutter, Hans-Peter-
dc.date.accessioned2018-10-24T14:11:05Z-
dc.date.available2018-10-24T14:11:05Z-
dc.date.issued1995-
dc.identifier.isbn0-7803-2431-5de_CH
dc.identifier.issn1520-6149de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/12118-
dc.description.abstractThe paper compares a newly proposed hybrid connectionist-SCHMM approach [Hutter and Pfister 1994] with other hybrid approaches. In the new approach a multilayer perceptron (MLP) replaces the conventional codebooks of semi-continuous HMMs. The MLP is therefore trained on so-called basic elements (phones and phone parts) in such a way that the outputs of the network estimate the a posteriori probabilities of these elements, given a context of input vectors. These a posteriori estimates are converted into scaled likelihoods, which are then used as observation probabilities in the framework of classical SCHMMs. The remaining parameters of the SCHMMs are trained with the well-known Baum-Welch algorithm using the estimated likelihoods of the MLP. This approach compared favorably with other proposed hybrid systems and classical approaches on an isolated German digit recognition task over telephone lines. It exhibited the highest recognition rate of all systems, followed by an approach using LVQ3 optimization of the codebook.de_CH
dc.language.isoende_CH
dc.publisherIEEEde_CH
dc.rightsLicence according to publishing contractde_CH
dc.subjectSpracherkennungde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleComparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognitionde_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Informatik (InIT)de_CH
zhaw.publisher.placeDetroitde_CH
dc.identifier.doi10.1109/ICASSP.1995.479693de_CH
zhaw.conference.details1995 International Conference on Acoustics, Speech, and Signal Processing, Detroit, USA, 9-12 May 1995de_CH
zhaw.funding.euNode_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end3314de_CH
zhaw.pages.start3311de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedings1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP)de_CH
zhaw.webfeedHuman Information Interactionde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.
Show simple item record
Hutter, H.-P. (1995). Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition [Conference paper]. 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 3311–3314. https://doi.org/10.1109/ICASSP.1995.479693
Hutter, H.-P. (1995) ‘Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition’, in 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Detroit: IEEE, pp. 3311–3314. Available at: https://doi.org/10.1109/ICASSP.1995.479693.
H.-P. Hutter, “Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition,” in 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1995, pp. 3311–3314. doi: 10.1109/ICASSP.1995.479693.
HUTTER, Hans-Peter, 1995. Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition. In: 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Conference paper. Detroit: IEEE. 1995. S. 3311–3314. ISBN 0-7803-2431-5
Hutter, Hans-Peter. 1995. “Comparison of a New Hybrid Connectionist-SCHMM Approach with Other Hybrid Approaches for Speech Recognition.” Conference paper. In 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 3311–14. Detroit: IEEE. https://doi.org/10.1109/ICASSP.1995.479693.
Hutter, Hans-Peter. “Comparison of a New Hybrid Connectionist-SCHMM Approach with Other Hybrid Approaches for Speech Recognition.” 1995 International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE, 1995, pp. 3311–14, https://doi.org/10.1109/ICASSP.1995.479693.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.