Richard Stern

Professor Richard Stern holds joint appointments in Electrical and Computer Engineering, Computer Science, and Biomedical Engineering at Carnegie Mellon University. His research bridges auditory perception with speech technology, particularly in developing noise-robust speech recognition systems. His PNCC algorithm revolutionized feature extraction for speech recognition in noisy environments.

Research emphases include:

• Auditory-inspired signal processing
• Robust automatic speech recognition
• Computational models of binaural hearing
• Music information retrieval
• Biomedical applications of audio analysis

Recent work demonstrates growing interest in human-robot interaction and respiratory monitoring applications. Publications increasingly incorporate deep learning while maintaining foundations in auditory physiology.

Honors include the IEEE Signal Processing Society 2019 Best Paper Award for PNCC research. Current projects investigate neural audio processing models and online learning for sound event detection.