Detección de vocales mediante modelado de clusters de fonemas

  1. Luengo Gil, Iker
  2. Navas Cordón, Eva
  3. Sánchez de la Fuente, Jon
  4. Hernáez Rioja, Inmaculada
Procesamiento del lenguaje natural

ISSN: 1135-5948

Year of publication: 2009

Issue: 43

Pages: 121-128

Type: Article

More publications in: Procesamiento del lenguaje natural


Many speech signal processing systems require the detection of regions of stability within the signal. As vowels form great stability regions, a system capable of detecting them automatically in the speech is very convenient. This work presents such a system, which uses HMM models of phonetic clusters created according to the acoustic similarities among the phonemes. These clusters are the key element for the system to work correctly in different languages. Although models were trained in Basque, tests were carried out in both Basque and German speech databases showing that the system is able to detect the vowels and their boundaries with acceptable accuracy in both languages.