A WAVELET-BASED SPEAKER VERIFICATION ALGORITHM

Autor(es)

Lacerda, Michel Alves ^[1] ; Guido, Rodrigo Capobianco ^[1] ; de Souza, Leonardo Mendes ^[1] ; Franchi Zulato, Paulo Ricardo ^[1] ; Ribeiro, Jussara ^[1] ; Chen, Shi-Huang ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Phys Sao Carlos, Dept Phys & Informat, SpeechLab FFI IFSC USP, BR-13566590 Sao Carlos, SP - Brazil

^[2] Shu Te Univ, Dept Comp Sci & Informat Engn, Yanchao 82445, Kaohsiung Cty - Taiwan

• Tipo de documento: Artigo Científico
• Fonte: INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING; v. 8, n. 6, p. 905-912, NOV 2010.
• Citações Web of Science: 1

Resumo

This paper presents a study on wavelets and their characteristics for the specific purpose of serving as a feature extraction tool for speaker verification (SV), considering a Radial Basis Function (RBF) classifier, which is a particular type of Artificial Neural Network (ANN). Examining characteristics such as support-size, frequency and phase responses, amongst others, we show how Discrete Wavelet Transforms (DWTs), particularly the ones which derive from Finite Impulse Response (FIR) filters, can be used to extract important features from a speech signal which are useful for SV. Lastly, an SV algorithm based on the concepts presented is described. (AU)

• Processo FAPESP: 05/00015-1 - Speechauth: desenvolvimento de um sistema para autenticação biométrica e interpretação de comandos através da análise de sinais de voz
• Beneficiário: Rodrigo Capobianco Guido
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores