Uso de técnicas acústicas para verificação de locutor em simulação experimental

Resumo

The aim of this research was to investigate the eciency of a set of acoustic measures to identify one randomly pre-selected individual, named “the
criminal”, out of a group of ten speakers of Brazilian Portuguese. Among the measures used were the first two formants of vowels, fundamental frequency, the duration of syllables and vowels, formant movement rate, intensity and the standard deviation of consonantal interval durations (∆C). We analyzed all the Brazilian Portuguese vowels. All the subjects were speakers of Brazilian Portuguese from the states of São Paulo, Rio Grande do Sul, Pará and Bahia. All the samples were extracted from interviews recorded in low quality acoustic environments.
The samples were divided into two groups i) interviews and ii) recorded telephone conversations (mobile phone to mobile phone). The parameters that were most robust were rhythm and timing, such as duration, speech rate, ∆C and formant movement rate for the second formant. Because of their interspeaker variability, timing measures proved to be highly discriminative. The statistical tests showed that the speech of three of the subjects contained similarities to that of “the criminal”.