Please use this identifier to cite or link to this item: https://dspace.upt.ro/xmlui/handle/123456789/3744
Title: Comparing various automatic speaker recognition approaches [articol]
Authors: Barbu, Tudor
Costin, Mihaela
Subjects: Speaker recognition
Speech feature vectors
Mel-frequency cepstral coefficients
Autoregressive (AR) coefficients
ART 2
Issue Date: 2004
Publisher: Timişoara : Editura Politehnica
Citation: Barbu, Tudor. Comparing various automatic speaker recognition approaches. Timişoara: Editura Politehnica, 2004
Series/Report no.: Buletinul ştiinţific al Universităţii „Politehnica” din Timişoara, România. Seria electronică şi telecomunicaţii, Tom 49(63), fasc. 1 (2004), p. 291-296
Abstract: Connectionist methods in speaker recognition give promising results on the condition of selecting a well balanced feature vector. Special attention has to be paid to the classifier procedure applied on the presented templates. We are discussing here several different speaker recognition methods, focusing on two main approaches: a MFCC supervised approach using a Hausdorff-based metric and an AR - ART2 structure (autoregressive features classified with an Adaptive Resonance Theory type 2 Network). Then, we report them to our previous results. These methods can function in a single or parallel structure, needing a weighted inference to accomplish the recognition task. Respecting the well known a-priories in signal treatment, and carefully selecting the frequency bands to be “examined”, our trials gave good results, with a mean detection error reduced with about 3% compared to our previous essays. Our studies concentrate on tests made with discrete-words, in real, noisy environment and real-time / off-line speaker verification.
URI: http://primo.upt.ro:1701/primo-explore/search?query=any,contains,Comparing%20various%20automatic%20speaker%20recognition%20approaches&tab=default_tab&search_scope=40TUT&vid=40TUT_V1&lang=ro_RO&offset=0 Link Primo
Appears in Collections:Articole științifice/Scientific articles

Files in This Item:
File Description SizeFormat 
BUPT_ART_Barbu_f.pdf805.87 kBAdobe PDFView/Open


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