Data mining applied to forensic speaker identification

P Univaso, JM Ale, JA Gurlekian - IEEE Latin America …, 2015 - ieeexplore.ieee.org
In this paper we analyze the advantages of using data mining techniques and tools for data
fusion in forensic speaker recognition. Segmental and suprasegmental features were …

[PDF][PDF] Modelado de estructuras prosódicas para el reconocimiento automático del habla

EM Albornoz, D Milone, H Rufiner - 2011 - sinc.unl.edu.ar
El término prosodia se utiliza para denominar a determinadas magnitudes físicas que
pueden ser medidas en las señales de voz, como ser la energía, la frecuencia fundamental …

[PDF][PDF] ING. PEDRO NR UNIVASO

DRLICJM ALE–FIUBA - 2019 - researchgate.net
Some of the most popular applications of speaker recognition are: financial, forensic and
legal, security, audio and video indexing, surveillance, teleconferencing, and elearning. This …

Classification of ASR Word Hypotheses using prosodic information and resampling of training data

EM Albornoz, DH Milone, HL Rufiner… - Latin American …, 2013 - SciELO Argentina
In this work, we propose a novel resampling method based on word lattice information and
we use prosodic cues with support vector machines for classification. The idea is to consider …

[PDF][PDF] New Method for Classification of ASR Word Hypotheses Using Prosodic Cues

EM Albornoz, DH Milone, HL Rufiner… - Latin American …, 2012 - sinc.unl.edu.ar
In this work, we propose a novel resampling method based on word lattice information and
we use prosodic cues with support vector machines for classification. The idea is to consider …