Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition

By Chanwoo Kim, Richard M. Stern. 2016

448 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Signal Processing

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 Natural Language Processing

In Signal Processing

Citations in the corpus

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (2019, methodology): “Additional robustness has been achieved through pre-processing techniques such as standardizing the statistics of the input (Liu et al., 1993; Torre et al., 2005; Harvilla & Stern, 2012; Kim & Stern, 2016).”
Approaches to Multi-domain Language Recognition (2018, background): “We considered several acoustic features in our systems, each of which are referenced in the following sections: power normalized cepstral coefficients [6] (PNCC), Mel frequency cepstral coefficients (MFCC), log Mel spectra (LMS), and 5th-order Legendre polynomials of pitch and voicing [7] (PROS).”
Transfer Learning from Audio-Visual Grounding to Speech Recognition (2019, background): “Such features can be hand-crafted by leveraging prior knowledge [11, 12, 13, 14], or they can be learned in a data-driven fashion.”
rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method (2019, background): “PNCCs [71] are known to be robust against noise.”
Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations (2018, methodology): “Additional robustness has been achieved through pre-processing techniques such as standardizing the statistics of the input [40, 54, 18, 35].”
Joint noise adaptive training for robust automatic speech recognition (2014, background): “But most such techniques assume Gaussian mixture model (GMM) based acoustic models (GMM-AMs); it is currently unclear how to extend them to DNN based systems.”
ABX-Discriminability Measures and Applications. (Mesures de discriminabilité ABX et applications) (2016, background): “[194, 195]) and models of aspects of human audition (e.”
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home (2017, background): “Traditional approaches for enhancing speech recognition accuracy in the presence of noise include beam forming [5], masking [6, 6, 7, 8, 9, 10], robust feature extraction [11, 12, 13, 14, 15], and auditory processing such as on-set enhancement [16, 17, 18, 19].”