Power-Normalized Cepstral Coefficients (PNCC) for robust speech recognition

By Chanwoo Kim, Richard M. Stern. 2012

193 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Oceanography, Natural Language Processing, Speech & Audio, 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 Oceanography

In Natural Language Processing

In Speech & Audio

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).”
Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition (2016, background): “These filters are specified in detail in [2, 3].”
rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method (2019, background): “PNCCs [71] are known to be robust against noise.”
Approaches to Multi-domain Language Recognition (2018, background): “…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…”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “For feature combination, this study concludes that the most effective feature set consists of PNCC, GF, and LOG-MEL for speech enhancement, and PNCC, GFCC, and LOG-MEL for speaker separation.”
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 [39, 53, 17, 34].”
The third 'CHiME' speech separation and recognition challenge: Analysis and outcomes (2017, result): “For example, Bagchi et al. (2015) report equivocal results when supplementing system input with robust features such as PNCC (Kim and Stern, 2012) and RASTA-PLP (Hermansky and Morgan, 1994), despite these same features having proved highly beneﬁcial in the previous artiﬁcially mixed CHiME-2 challeng”