Detail publikace

Automatic Speaker Recognition by Speech Signal

Originální název

Automatic Speaker Recognition by Speech Signal

Anglický název

Automatic Speaker Recognition by Speech Signal

Jazyk

en

Originální abstrakt

Speaker recognition is the complement of speech recognition. In automatic speech recognition, the speech processing approach tries to extract linguistic information from the speech signal to the exclusion of personal information. Conversely, speaker recognition is focused on the characteristics unique to the individual, disregarding the current word spoken. An ideal speaker recognition system would use only physical features to characterize speakers, since these features cannot be easily changed. Numerical values for physical features or parameters would have to be derived from digital signal processing parameters extracted from the speech signal.

Anglický abstrakt

Speaker recognition is the complement of speech recognition. In automatic speech recognition, the speech processing approach tries to extract linguistic information from the speech signal to the exclusion of personal information. Conversely, speaker recognition is focused on the characteristics unique to the individual, disregarding the current word spoken. An ideal speaker recognition system would use only physical features to characterize speakers, since these features cannot be easily changed. Numerical values for physical features or parameters would have to be derived from digital signal processing parameters extracted from the speech signal.

BibTex


@inbook{BUT55217,
  author="Milan {Sigmund}",
  title="Automatic Speaker Recognition by Speech Signal",
  annote="Speaker recognition is the complement of speech recognition. In automatic speech recognition, the speech processing approach tries to extract linguistic information from the speech signal to the exclusion of personal information. Conversely, speaker recognition is focused on the characteristics unique to the individual, disregarding the current word spoken. An ideal speaker recognition system would use only physical features to characterize speakers, since these features cannot be easily changed. Numerical values for physical features or parameters would have to be derived from digital signal processing parameters extracted from the speech signal.",
  address="In-Tech Education and Publishing",
  booktitle="Zemliak A., Frontiers in Robotics, Automation and Control",
  chapter="55217",
  edition="Advanced Robotics Series",
  howpublished="print",
  institution="In-Tech Education and Publishing",
  year="2008",
  month="november",
  pages="41--54",
  publisher="In-Tech Education and Publishing",
  type="book chapter"
}