Sammenlign metoder

	MFCC (Mel-Frequency Cepstral Coefficients)	Ambisonics	Uafhængig Vektor Analyse
Fagområde	Anvendt fysik	Anvendt fysik	Anvendt fysik
Familie	Process / pipeline	Process / pipeline	Process / pipeline
Oprindelsesår	1980	1973	2007
Ophavsperson	Steven Davis, Paul Mermelstein	Michael Gerzon	Tae-Won Lee, Mark Lewicki, Terrence Sejnowski
Type	Audio feature extraction algorithm	Spatial audio encoding and reproduction technique	Multivariate matrix decomposition algorithm
Oprindelig kilde	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.	Gerzon, M. A. (1973). Periphony: with-height sound reproduction. Journal of the Audio Engineering Society, 21(1), 2-10.	Lee, T. W., Lewicki, M. S., & Sejnowski, T. J. (2007). Independent Component Analysis for Source Localization in Biomedical Signals. In Proc. IEEE Int. Conf. Acoust. Speech Signal Process., pp. 97-100.
Aliasser	mel-cepstral features, MFCC features, mel-frequency features	spatial audio, B-format, ambisonic recording	IVA, multivariate ICA, vector blind source separation
Relaterede	3	3	3
Resumé	Mel-Frequency Cepstral Coefficients (MFCCs) are a compact representation of audio features that mimic human auditory perception. Introduced by Davis and Mermelstein in 1980, MFCCs are the de facto feature extraction method for speech recognition and environmental sound analysis. They compress the frequency information of audio signals into a small set of coefficients that capture phonetic content while discarding irrelevant details.	Ambisonics is a full-sphere spatial audio encoding and reproduction technique that captures and reproduces three-dimensional sound fields. Developed by Michael Gerzon in the 1970s, it uses spherical harmonics to represent sound at all directions around a central point. Unlike surround systems that use discrete channels, Ambisonics provides a format-agnostic spatial representation that can be rotated, translated, and rendered to any speaker configuration.	Independent Vector Analysis (IVA) is a multivariate extension of Independent Component Analysis that jointly separates multiple datasets while maintaining dependencies within each dataset. Developed by Lee, Lewicki, and Sejnowski in the 2000s, IVA is used for blind source separation in multi-channel audio, brain imaging, and signal processing. It exploits both the independence between sources and correlations within frequency bands or time-frequency structures.