Delta-spectral cepstral coefficients for robust speech recognition

By Kshitiz Kumar, Chanwoo Kim, Richard M. Stern. 2011

128 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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

1. Chanwoo Kim
2. Richard M. Stern
3. Dan Hendrycks
4. Thomas G. Dietterich
5. Yu Zhang
6. Yonghui Wu

In Speech & Audio

1. Chanwoo Kim
2. Richard M. Stern
3. Dan Hendrycks
4. Thomas G. Dietterich

In Signal Processing

1. Chanwoo Kim
2. Richard M. Stern
3. Dan Hendrycks
4. Thomas G. Dietterich
5. Wei-Ning Hsu

Citations in the corpus

• Learning Robust and Multilingual Speech Representations (2020, neutral): “For acoustic representations, it is known that the standard MFCC features are sensitive to additive noise and many mod-ifications have been proposed to overcome those limitations (Dev and Bansal, 2010; Kumar et al., 2011).”
• Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition (2016, background): “…been significantly revised to address these issues in a fashion that enables it to provide superior recognition accuracy over a broad range of conditions of noise and reverberation using features that are computable in real time using " online " algorithms that do not require extensive look-ahead,…”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “The mel-domain features 604 are MFCC and delta-spectral cepstral coefficient (DSCC) [104], 605 which is similar to MFCC except that a delta operation is ap- 606 plied to mel-spectrum.”