While voice activity detection is considered as a must-have for a growing range of applications such as wearable devices or smart home appliances, Dolphin Integration innovates with the stand-alone WhisperTrigger™. Whereas the voice detection function is usually handled by a DSP or a voice processor, it now becomes possible to leave the rest of the SoC in stand-by or sleep mode while leaving only the WhisperTrigger™ in always-on mode. Indeed, it enables to wake-up the system without voice data loss.
Depending on the choice of microphone either Digital or Analog, two triggers are available WhisperTrigger D and A.
The WhisperTriggers, designed as hard Silicon IP, are ideally suited for triggering voice recognition algorithms thanks to their low detection latency enabling faster wake-up of the voice Processor.
Performance highlights of WhisperTrigger-D for a digital MEMS microphone:
- Saving up to 30 % of DSP activity due to an efficient detection algorithm, avoiding numerous false detections compared to power-based algorithms
- Ultra-low power consumption: only 15 μW added to codec stand-by mode consumption for Voice Detection
- Detection Latency (DL): down to 8 ms depending on the type of phoneme
- Noise Detected as Speech Rate (NDSR): 8 % at 10 dB of Power Ratio (PwR) threshold level.
WhisperTrigger™ is embedded in several products of our portfolio:
- sCODa96-H1-LB-IO-VD.01 (28 nm)
- sCODS100-LB-IO-N.12 (40 nm)
- sCODp-MT1-VD.02 (130 nm)
For further information, please contact – converters@dolphin-ip.com.
