Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, SHen_US
dc.contributor.authorLiao, YFen_US
dc.contributor.authorChiang, SMen_US
dc.contributor.authorChang, SGen_US
dc.date.accessioned2019-04-02T05:59:22Z-
dc.date.available2019-04-02T05:59:22Z-
dc.date.issued1998-01-01en_US
dc.identifier.issn1063-6676en_US
dc.identifier.urihttp://dx.doi.org/10.1109/89.650315en_US
dc.identifier.urihttp://hdl.handle.net/11536/148312-
dc.description.abstractA novel recurrent neural network-based (RNN-based) front-end preclassification scheme for fast continuous Mandarin speech recognition is proposed in this paper, First, an RNN is employed to discriminate each input frame for the three broad classes of initial, final, and silence, A finite state machine (FSM) is then used to classify the input frame into four states including three stable states of Initial (I), Final (F), and Silence (S), and a Transient (T) state, The decision is made based on examining whether the RNN discriminates well between classes, We then restrict the search space for the three stable states in the following DP search to speed up the recognition process, Efficiency of the proposed scheme was examined by simulations in which we incorporate it with a hidden Markov model-based (HMM-based) continuous 411 Mandarin base-syllables recognizer, Experimental results showed that it can be used in conjunction with the beam search to greatly reduce the computational complexity of the HMM recognizer while keeping the recognition rate almost undegraded.en_US
dc.language.isoen_USen_US
dc.titleAn RNN-based preclassification method for fast continuous Mandarin speech recognitionen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/89.650315en_US
dc.identifier.journalIEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSINGen_US
dc.citation.volume6en_US
dc.citation.spage86en_US
dc.citation.epage90en_US
dc.contributor.department電信工程研究所zh_TW
dc.contributor.departmentInstitute of Communications Engineeringen_US
dc.identifier.wosnumberWOS:000071264800009en_US
dc.citation.woscount7en_US
Appears in Collections:Articles