ScholarGate
Assistent
Process / pipelineAudio Signal Processing

MFCC (Mel-Frequency Cepstral Coefficients)

Mel-Frequency Cepstral Coefficients (MFCCs) er en kompakt repræsentation af lydfunktioner, der efterligner menneskelig auditiv perception. Introduceret af Davis og Mermelstein i 1980, er MFCCs de facto feature-ekstraktionsmetoden til talegenkendelse og analyse af miljølyde. De komprimerer frekvensinformationen af lydsignaler til et lille sæt koefficienter, der indfanger fonetisk indhold, mens irrelevant detaljer kasseres.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

MFCC (Mel-Frequency Cepstral Coefficients)
AmbisonicsHovedrelateret overførin…Uafhængig Vektor Analyse

Kilder

  1. Davis, S., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(4), 357-366. DOI: 10.1109/TASSP.1980.1163420
  2. Young, S. J., Evermann, G., Gales, M. J., et al. (1996). The HTK Book. Cambridge University Engineering Department. link
  3. Moustakides, G. V., & Rougui, J. A. (2004). Optimal filtering for polynomial signal models. IEEE Transactions on Signal Processing, 52(8), 2219-2230. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Mel-Frequency Cepstral Coefficients. ScholarGate. https://scholargate.app/da/applied-physics/mfcc

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Refereret af

ScholarGateMFCC (Mel-Frequency Cepstral Coefficients). Hentet 2026-06-15 fra https://scholargate.app/da/applied-physics/mfcc · Datasæt: https://doi.org/10.5281/zenodo.20539026