Our Products
Panda Agent Voiceprint Recognition Algorithm System
Voiceprint Recognition / Offline AI
Voiceprint RecognitionOffline AIEdge Deployment
Product Overview
Based on the WeSpeaker ResNet34 deep neural network model, it provides fully offline speaker enrollment and recognition capabilities. No internet connection required, supports local inference on edge devices, with recognition latency as low as 84ms (for 5-second speech). Suitable for scenarios with strict privacy and real-time requirements such as quadruped robots, industrial equipment, and smart access control.
Key Features
| Speaker Enrollment | Capture ≥3s speech, extract 256-dimensional voiceprint feature vector and store in database |
| Speaker Recognition | Compare with voiceprint database, output best match and similarity score |
| Multi-user Voiceprint Database | Supports simultaneous enrollment of multiple users, verified for ≥4 concurrent recognition |
| Fully Offline | Local ONNX inference, zero network dependency, data never leaves edge device |
| Edge Deployment | Supports Jetson Orin CPU/CUDA/TensorRT |
| Real-time Response | RTF approx. 0.045, processing speed about 22 times real-time |
| USB Microphone | Supports 16kHz mono audio capture, plug-and-play without drivers |
| Result Announcement | Recognition results output in real-time via USB speaker or UART |
Technical Specifications
| Base Model | WeSpeaker ResNet34 CnCeleb (ONNX float32, 25.3MB) |
| Feature Dimension | 256-dimensional Speaker Embedding |
| Inference Latency | 5s audio CPU single-thread 227ms / 2-thread 134ms / 4-thread 91ms |
| RTF | Approx. 0.045 |
| Runtime Environment | Python 3.8+, sherpa-onnx, ONNX Runtime, Ubuntu 20.04 |
Typical Applications
Quadruped Robot Identity AuthenticationIndustrial Equipment Voiceprint Access ControlSmart SecurityVoice Command AuthorizationAttendance Verification