Full metadata record
DC FieldValueLanguage
dc.contributor.authorWANG, YRen_US
dc.contributor.authorCHEN, SHen_US
dc.date.accessioned2014-12-08T15:03:42Z-
dc.date.available2014-12-08T15:03:42Z-
dc.date.issued1994-11-01en_US
dc.identifier.issn0001-4966en_US
dc.identifier.urihttp://dx.doi.org/10.1121/1.411274en_US
dc.identifier.urihttp://hdl.handle.net/11536/2248-
dc.description.abstractIn this paper, a simple recurrent neural network (SRNN) is employed to model the prosody of continuous Mandarin speech to assist tone recognition. For each syllable in continuous speech, several acoustic features carrying prosodic information are extracted and taken as inputs to the SRNN. If proper linguistic features extracted from the context of the syllable are set as output targets, the SRNN can learn to represent the prosodic state of the utterance at the syllable using its hidden nodes. Outputs of the hidden nodes then serve as additional recognition features to assist recognition of the tone of the syllable. The performance of the proposed tone recognition approach was examined by simulation on a multilayer perception (MLP)-based speaker-dependent tone recognition task. The recognition rate was improved from 91.38% to 93.10%. The SRNN prosodic model is further analyzed to exploit the linguistic meaning of prosodic states. By vector quantizing the outputs of the hidden nodes of the SRNN, a finite-state automata that roughly represents the mechanism of human prosody pronunciation can be obtained.en_US
dc.language.isoen_USen_US
dc.titleTONE RECOGNITION OF CONTINUOUS MANDARINE SPEECH ASSISTED WITH PROSODIC INFORMATIONen_US
dc.typeArticleen_US
dc.identifier.doi10.1121/1.411274en_US
dc.identifier.journalJOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICAen_US
dc.citation.volume96en_US
dc.citation.issue5en_US
dc.citation.spage2637en_US
dc.citation.epage2645en_US
dc.contributor.department電信工程研究所zh_TW
dc.contributor.department電信研究中心zh_TW
dc.contributor.departmentInstitute of Communications Engineeringen_US
dc.contributor.departmentCenter for Telecommunications Researchen_US
dc.identifier.wosnumberWOS:A1994PQ01800002-
dc.citation.woscount13-
Appears in Collections:Articles


Files in This Item:

  1. A1994PQ01800002.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.