- AI IP for Cybersecurity monitoring - Smart Monitor
- ARC EV Processors are fully programmable and configurable IP cores that are optimized for embedded vision applications
- Enhanced Neural Processing Unit for safety providing 32,768 MACs/cycle of performance for AI applications
- EV74 processor IP for AI vision applications with 4 vector processing units
- EV7x Vision Processors
- EV7xFS Vision Processors for Functional Safety
- More Products...
IP-SOC DAYS 2025 IP-SOC DAYS 2024 IP-SOC DAYS 2023 IP-SOC DAYS 2022 IP-SOC DAYS 2021 IP-SOC 2024 IP-SOC 2023 IP-SOC 2022 IP-SOC 2021
|
|||||||
![]() |
|

CEA-Leti Develops Novel Architecture for Keyword-Spotting (KWS) In Always-On, Voice-Activated Edge-AI Systems
- Designing the future: AI innovation accelerated through university collaboration
- Synopsys strengthens India's role with push for world's first AI-based chip foundry
- Quantropi brings post-quantum cryptography to STM32 just in time to face new threats
- New architecture for AI datacentres proposed
- How AI is Pushing Semiconductor Manufacturing into a Generational Shift
- Keysight Supports Post-Quantum Cryptography Evaluation (Jul. 24, 2025)
- Mixel Supports Automotive SerDes Alliance (ASA) Motion Link SerDes IP (Jul. 23, 2025)
- TSMC to Exit GaN, Focus on Advanced Packaging (Jul. 23, 2025)
- UMC Announces Software Acquisition and Upcoming Earnings Release (Jul. 23, 2025)
- Arteris Selected by Whalechip for Near-Memory Computing Chip (Jul. 22, 2025)
- See Latest News>>
GRENOBLE, France – Feb. 21, 2024 – CEA-Leti has developed a keyword-spotting system that dramatically improves accuracy in always-on, voice-activated Edge-AI systems and that consumes less power in a far smaller silicon footprint than current technology.
www.leti-cea.com/cea-tech/leti/english, Feb. 21, 2024 –
Presented in a paper at ISSCC 2024 in San Francisco, the new architecture uses time-domain signal processing on oscillators locked by injection and is suitable for devices running on energy harvesters, which supply power below 0.5V. The paper, "0.4V 988nW Time-Domain Audio Feature Extraction for Keyword Spotting Using Injection-Locked Oscillators", reports accurate speech recognition at power consumption below one microwatt.
It describes the first injection-locked, oscillator-based time-domain audio feature extraction (TD-FEx) demonstrating keyword spotting operating down to 0.4V, while achieving 91 percent accuracy on 10 words. TD-FEx information is not coded as a voltage but as a time delay of two clocks' signals. In addition to being well suited for advanced nodes, its advantages are digital-like implementation with low-supply voltage and better noise immunity than current systems. CEA-Leti's system demonstrated accurate speech recognition with power consumption below 1 µW.
Some analog-based audio feature extraction (FEx) units using multi-channel Gm-C bandpass filters can supply 10 times the power efficiency of digital FEx units in a comparable silicon area. "However, analog FEx circuits have not demonstrated KWS with more than four keywords," the paper reports. "They also suffer from a large footprint, challenging technology migration and limited dynamic range at low supply voltage, while speech signals have inherently a high dynamic range."