Linear prediction and discrete wavelet transform to identify pathology in voice signals

• Autor(a) principal: Fonseca, Everthon Silva [UNESP]
• Data de Publicação: 2017
• Outros Autores: Pereira, Denis Cesar Mosconi, Maschi, Luis Fernando Castilho, Guido, Rodrigo Capobianco [UNESP], Paulo, Katia Cristina Silva [UNESP]
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1109/SPS.2017.8053638; http://hdl.handle.net/11449/179379
• topic: pathologies; prediction; signals; voice; wavelet

This work describes an algorithm to help in the identification of pathologically affected voices. Based on inverse linear prediction filter (LPC) and discrete wavelet transform (DWT), this method can be used in conjunction with other classifiers in order to improve them, by the addition of the new parameter we propose, DWT-RMS. Using no association with other methods, DWT-RMS gives quantitative evaluation of voice signals from male and female subjects of different ages and leads to an adequate larynx pathology classifier with 85.94% of classification accuracy, 0% of false negatives and 14.06% of false positives, to identify nodules in vocal folds.