Per-Channel Energy Normalization: Why and How

• Published in: IEEE signal processing letters Vol. 26; no. 1; pp. 39 - 43
• Main Authors: Lostanlen, Vincent, Salamon, Justin, Cartwright, Mark, McFee, Brian, Farnsworth, Andrew, Kelling, Steve, Bello, Juan Pablo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Acoustic noise; acoustic sensors; acoustic signal detection; Acoustics; Adequacy; Automatic speech recognition; Compression; Computer Science; Dynamic range; Frequencies; Frequency modulation; Gain control; Noise; Noise measurement; Pattern recognition; Random noise; signal classification; Sound; Spectrogram; Speech recognition; Time-frequency analysis; Voice recognition

In the context of automatic speech recognition and acoustic event detection, an adaptive procedure named per-channel energy normalization (PCEN) has recently shown to outperform the pointwise logarithm of mel-frequency spectrogram (logmelspec) as an acoustic frontend. This letter investigates the ad...