Satheesh PK
Satheesh is a DSP engineer with over 20 years of experience specializing in digital audio, speech, and image processing. Throughout his career, he has developed advanced algorithms that are now integrated into some of the world’s leading mobile phones. His expertise includes both hands-on algorithm development and leading technical teams to deliver innovative solutions.
Currently, he works as a freelance developer, focusing on cutting-edge noise reduction systems for automotive applications and designing custom chatbot solutions for clients across the globe. Previously, he served as Associate Technical Director at Samsung Semiconductor India R&D Centre, where he led the Automotive Division’s algorithm development team. In this role, he delivered multimedia and computer vision software components, including deep learning-based echo cancellation, multi-channel active noise control, and audio sample rate converters, with significant implementation on Cadence HiFi DSPs.
Earlier in his career, he contributed to major audio and speech signal processing projects and played a significant role in optimizing audio algorithms for both efficiency and high-fidelity user experiences across diverse hardware platforms, such as ARM, Wolfson Audio DSP, and Tensilica HiFi architectures. His core technical strengths include audio signal processing, multi-rate processing, noise reduction, echo cancellation, and floating to fixed-point conversion, with a background in neural networks and deep learning.
He holds a Bachelor of Technology in Electronics and Communication Engineering from the Government College of Engineering, Kannur, and a postgraduate diploma in embedded systems and digital signal processing from IIITM-K.
Recent Advancements In ML-Based Speech Enhancement Techniques
Status: Not yet available - Stay tuned!Recent advancements in machine learning-based speech enhancement focus on sophisticated deep learning models—including deep neural networks (DNNs), transformer architectures, and generative models—engineered for robust, real-time performance, personalization, and adaptability across varied acoustic environments.
The presentation will address key developments in speech enhancement such as:
- Quality-optimized and task-specific model architectures
- Real-time and edge-oriented implementations
- Multichannel and spatially aware signal processing
- Generative data augmentation methods
- Applications of self-supervised and foundation models
- Unified frameworks supporting both personalized and general speech enhancement