Bhiksha Raj
Papers
1
Total Citations
5
H-Index
1
About
Bhiksha Raj is a leading figure in speech and audio processing, with foundational contributions to distant speech recognition, microphone array processing, and machine learning for audio. His work on spherical microphone arrays has been instrumental in enabling robust speech capture in noisy, real-world environments—a critical step toward natural human-computer interaction. Raj’s research also spans deep learning for speech separation, speaker recognition, and interpretable AI, where he has advanced methods for understanding and improving model behavior. With over 5,000 citations, his impact is evident across both theoretical and applied domains. Notably, his work on microphone array processing for distant speech recognition, including the influential 2012 paper on spherical arrays, has shaped modern voice-controlled systems like smart speakers and the Microsoft Kinect. Raj is also recognized for his contributions to adversarial robustness in audio and for mentoring a generation of researchers at Carnegie Mellon University, where he is a professor. His blend of signal processing rigor and machine learning innovation continues to drive progress in making machines hear as humans do.
Research Focus
Key Achievements
Top Papers
- 1