Hardware Podcasts

Episode 139: Advanced robot hearing - Christine Evers

Robot Talk · 9 Jan 2026 · 28m · Episode 139

What this episode covers

Christine Evers, Director of the Centre for Robotics at the University of Southampton, discusses bio-inspired machine listening that enables robots to understand complex acoustic environments. She explains how embedding human auditory processing into deep learning architectures creates efficient, interpretable models suitable for resource-constrained robots, moving away from massive, energy-hungry internet-scale models. The conversation covers the challenges of ego noise, the need for spatial awareness via microphone arrays, and the concept of 'active audition' where robot movement shapes auditory perception.

Most relevant to

established companies

Topics

Mentioned

Companies
University of Southampton
Also
Centre for Robotics, UKRI trustworthy autonomous system, Responsible AI UK

Related episodes from other shows

Other shows on the same ground, closest first.

  • EE Times Current · 44m

    Giving the Humanoid iCub Embodied, Neuromorphic Vision

    Dr. Chiara Bartolozzi of the Italian Institute of Technology discusses implementing neuromorphic vision and attention mechanisms on the iCub humanoid robot. She explains the challenges of processing event-driven data from dynamic vision sensors (DVS) and the necessity of embodiment to simplify perception tasks through active sensing. The conversation also covers the need for a solid theoretical framework for neuromorphic computing and the trade-offs between biological plausibility and engineering efficiency.

    Sensors & measurement in productsEmbedded firmware
    9 chapters

  • The Next Byte Podcast · 28m

    104. Recapping 2022

    Hosts Daniel and Forbode recap their top four episodes from 2022, covering biomimicry inspired by dandelion seeds, AI curiosity models like DALL-E, wearable sleep apnea detection, and sustainable hydropower turbines. They discuss the ethical implications of generative AI, the challenges of explaining complex topics like reinforcement learning to a lay audience, and their podcast's growth metrics, including a shift in global listenership away from the US. The hosts also outline goals for 2023, such as improving community engagement, producing better swag, and rebranding the show.

    AI & machine learningConnected products & IoT
    6 chapters

  • EE Times Current · 45m

    Why Sound Processing Takes Time, Not Just Frequency

    Dr. Shih-Chii Liu, co-director of the Sensors Group at the Institute of Neuroinformatics (ETH Zurich), explains how her neuromorphic silicon cochlea converts sound into asynchronous spikes to enable low-power voice activity detection. She details the use of delta modulation for faithful signal representation and 'delta networks' that leverage activation sparsity to reduce energy consumption by over 50%. Professor Ralph Etienne-Cummings of Johns Hopkins University discusses the historical context of silicon cochleas, citing early work by Carver Mead and Andre van Schaik, and their commercial applications in hearing aids and sound localization.

    Analog & power electronicsEmbedded firmware
    7 chapters

  • EE Times Current · 44m

    Neurons Close the Loop from Insect Perception to Action

    Professor Barbara Webb of the University of Edinburgh explains how she uses physical robots to validate neural mechanisms in crickets, ants, and bees, demonstrating that biological cognition requires complete sensory-motor loops. She details her work on cricket sound localization using analog electronics for precise timing, bee path integration via the central complex, and ant grasping mechanics using passive hairs. The discussion highlights the value of embodied robotics in testing biological hypotheses and inspiring efficient, low-power robotic control strategies.

    Mechanical engineeringEmbedded firmware
    8 chapters

  • The Next Byte Podcast · 19m

    103. Ant Inspired Swarm Robots

    Hosts Daniel and Forbode discuss a Harvard University research project that mimics ant colony behavior to create a decentralized swarm robotics system called 'RANTS'. They explain how the robots use 'photo-pheromones' (light gradients) to coordinate excavation tasks without central control, offering a lightweight alternative to complex AI. The episode also touches on the hosts' sponsor segment regarding IoT solutions for traffic congestion.

    Robotics & autonomyAI & machine learning
    4 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Robot Talk. The episode itself belongs to its publisher.