Constant Q cepstral coefficients: A spoofing countermeasure for automatic speaker verification
By Massimiliano Todisco, Héctor Delgado, N. Evans. Computer Speech and Language, 2017
485 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Signal Processing
View Paper: https://www.semanticscholar.org/paper/4dbe43d67677f1371a7ac6f9072c9fd4fe9c9f87
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
- Junichi Yamagishi
- N. Evans
- Massimiliano Todisco
- Xin Eric Wang
- Héctor Delgado
- Kong Aik LEE
- Tomi H. Kinnunen
- Andreas Nautsch
In Signal Processing
- Junichi Yamagishi
- N. Evans
- Massimiliano Todisco
- Ross Cutler
- Xin Eric Wang
- Héctor Delgado
- Chandan K. A. Reddy
- Kong Aik LEE
Citations in the corpus
- Non-intrusive Speech Quality Assessment Using Neural Networks (2019, methodology): “Applying the CQT allows better time-frequency resolution as described in [13].”
- ASVspoof 2019: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan ∗ (2021, background): “They are based on two different acoustic frontends, namely linear frequency cepstral coefficients [16] (LFCC) and constant Q cepstral coefficients [17] (CQCC).”
- The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection (2017, background): “Data heterogeneity has proven essential to the development of reliable spoofing countermeasures [21, 22, 23].”
- WIRE: Wavelet Implicit Neural Representations (2023, methodology): “ConstantQ Gabor wavelets are often used in music analysis [8, 46], wavelet transforms [24], and the Laplace transform.”