Detail publikace

Search for Keywords and Vocal Elements in Audio Recordings

Originální název

Search for Keywords and Vocal Elements in Audio Recordings

Anglický název

Search for Keywords and Vocal Elements in Audio Recordings

Jazyk

en

Originální abstrakt

This paper deals with search for keywords and non-verbal vocal elements in stored audio recordings. An efficient detection of some specific words or sounds embedded in continuous speech is based on isolated word recognition approaches. The mel-frequency cepstral coefficients and combination of predictive coefficients and autocorrelation coefficients are used in the speech signal analysis. A keyword slides along the stored speech signal and in each of its positions the distance, i.e. the similarity, to the corresponding speech segment of investigated utterance is computed.

Anglický abstrakt

This paper deals with search for keywords and non-verbal vocal elements in stored audio recordings. An efficient detection of some specific words or sounds embedded in continuous speech is based on isolated word recognition approaches. The mel-frequency cepstral coefficients and combination of predictive coefficients and autocorrelation coefficients are used in the speech signal analysis. A keyword slides along the stored speech signal and in each of its positions the distance, i.e. the similarity, to the corresponding speech segment of investigated utterance is computed.

Dokumenty

BibTex


@article{BUT102579,
  author="Milan {Sigmund}",
  title="Search for Keywords and Vocal Elements in Audio Recordings",
  annote="This paper deals with search for keywords and non-verbal vocal elements in stored audio recordings. An efficient detection of some specific words or sounds embedded in continuous speech is based on isolated word recognition approaches. The mel-frequency cepstral coefficients and combination of predictive coefficients and autocorrelation coefficients are used in the speech signal analysis. A keyword slides along the stored speech signal and in each of its positions the distance, i.e. the similarity, to the corresponding speech segment of investigated utterance is computed.",
  chapter="102579",
  number="9",
  volume="19",
  year="2013",
  month="november",
  pages="71--74",
  type="journal article - other"
}