| Field | Response |
|---|---|
| Intended Domain: | Voice Activity Detection (VAD) |
| Model Type: | Convolutional Neural Network (CNN) |
| Intended Users: | Developers, Speech Processing Engineers, AI Researchers |
| Output: | Sequence of speech probabilities for each 20 millisecond audio frame |
| Describe how the model works: | The model processes input audio by extracting spectrogram features, which are then passed through MarbleNet—a lightweight CNN-based model designed for VAD. The CNN learns to detect patterns associated with speech activity and outputs a probability score indicating the presence of speech in each 20 millisecond frame |
| Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable |
| Technical Limitations: | The model operates on 20 millisecond frames. While it supports longer frames by breaking them into smaller segments, it does not support outputs with a finer granularity than 20 milliseconds. |
| Verified to have met prescribed NVIDIA quality standards: | Yes |
| Performance Metrics: | Accuracy (False Positive Rate, ROC-AUC score), Latency, Throughput |
| Potential Known Risks: | While the model was trained on a limited number of languages, including Chinese, English, French, Spanish, German, and Russian, the model may experience a degradation in quality for languages and accents that are not included in the training dataset |
| Licensing: | NVIDIA Open Model License Agreement |