Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task

By T. Ganchev, N. Fakotakis, G. Kokkinakis. 2007

376 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Greedy InfoMax for Biologically Plausible Self-Supervised Representation Learning (2019, methodology): “The traditional, hand-engineered MFCC features are commonly used in speech recognition systems [Ganchev et al., 2005] and improve over the random features but provide limited linear separability on both tasks.”
Essentia: An Audio Analysis Library for Music Information Retrieval (2013, methodology): “• the energy of the given frequency band or the set of bands of a spectrum, the Bark band energies [51] of a spectrum, the Mel band energies and the Melfrequency cepstral coefficients of a spectrum using the MFCC-FB40 algorithm [21]; • the ERB band energies of a spectrum [49] and the Gammatone featu”
Putting An End to End-to-End: Gradient-Isolated Learning of Representations (2019, methodology): “The traditional, hand-engineered MFCC features are commonly used in speech recognition systems [Ganchev et al., 2005], and improve over the random features, but provide limited linear separability on both tasks.”
Emotional voice conversion using deep neural networks with MCC and F0 features (2016, background): “Before training them, we need to transform the MFCC features to MCC features for the DBNs model and transform the F0 features to the normalized-segment-F0 features (NSF0), respectively.”