PreVox™ Neural RT-10 is a real-time neural noise cancellation and speech enhancement solution for embedded systems, designed as a pre-processor for vocoders.  It offers the best balance between quality and latency, ensuring cleaner input for any voice codec.

• Neural, causal core. It’s based on a compact causal neural network.
• Vocoding pre-processor: improves codec efficiency by feeding it with cleaner speech.
• Low latency. Typically 10–20 ms algorithmic delay (configurable).
• Higher quality. Cleaner speech in stationary & non-stationary noise; no “musical noise,” natural prosody retained.
• Customer retraining. We adapt the model to your noise profiles and device acoustics.
• Optimized for ARM & DSP. Runs on ARM (Cortex-A/M/R, NEON) and common DSP cores (e.g., TI).

Please contact us for details.