Effective use of DCTS for contextualizing features for speaker recognition
ICASSP, pp. 4027-4031, 2014.
speaker recognitionmost energized coefficientsanalysis window sizemel filter bank outputsdiscrete cosine transformMore(24+)
This article proposes a new approach for contextualizing features for speaker recognition through the discrete cosine transform (DCT). Specifically, we apply a 2D-DCT transform on the Mel filterbank outputs to replace the common Mel frequency cepstral coefficients (MFCCs) appended by deltas and double deltas. A thorough comparison of algo...More
Full Text (Upload PDF)
PPT (Upload PPT)