A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients

By Massimiliano Todisco, Héctor Delgado, N. Evans. The Speaker and Language Recognition Workshop, 2016

381 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ed9c8b5ae425420ab1e85f65c22b11004dd8e4d0

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verification (2017, methodology): “Results reported here are the same as those published previously in (Todisco et al., 2016).”
ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems (2019, methodology): “Specifically, we use the official ASVspoof 2017 Challenge baseline CQCC-GMM model [34] using constant Q cepstral coefficients (CQCC) [13, 35] features and Gaussian mixture model (GMM) classifier and use exactly the same hyper-parameters.”
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection (2019, methodology): “They use a common Gaussian mixture model (GMM) back-end classifier with either constant Q cepstral coefficient (CQCC) features [22, 23] (B01) or linear frequency cepstral coefficient (LFCC) features [24] (B02).”
The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection (2017, methodology): “They use a common Gaussian mixture model (GMM) back-end classifier with constant Q cepstral coefficient (CQCC) features [20] which are based on a perceptually motivated time-frequency transform [29].”
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (2019, methodology): “Both use a common Gaussian mixture model (GMM) back-end classifier with either constant-Q cepstral coefficient (CQCC) features [64, 65] (B01) or linear frequency cepstral coefficient (LFCC) features [66] (B02).”
One-Class Learning Towards Synthetic Voice Spoofing Detection (2020, background): “Filter Cepstral Coefficients Instantaneous Frequency (CFCCIF) [8], Linear Frequency Cepstral Coefficients (LFCC) [9], and Constant-Q Cepstral Coefficients (CQCC) [10].”
STC Antispoofing Systems for the ASVspoof2019 Challenge (2019, methodology): “Additionally, we considered cepstral coefficients from baseline systems, proposed by the organisers of the ASVspoof2019: Linear Frequency Cepstral Coefficients (LFCC) [8] obtained by the use of triangular filters in linear space for local integration of the power spectrum and Constant Q Cepstral Coe”