Statements (43)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:signal_processing
gptkb:technology |
| gptkbp:alsoKnownAs |
gptkb:VAD
|
| gptkbp:category |
gptkb:public_speaker
audio signal processing |
| gptkbp:developedBy |
1970s
|
| https://www.w3.org/2000/01/rdf-schema#label |
Voice Activity Detection
|
| gptkbp:implementedIn |
gptkb:machine_learning
statistical models deep neural networks spectral features energy thresholding zero-crossing rate |
| gptkbp:importantFor |
improving speech quality
reducing bandwidth in speech transmission saving power in mobile devices speech endpointing |
| gptkbp:improves |
deep learning
machine learning methods |
| gptkbp:input |
audio signal
|
| gptkbp:limitation |
sensitivity to noise
difficulty in low SNR environments |
| gptkbp:output |
speech/non-speech decision
|
| gptkbp:relatedTo |
endpoint detection
speech activity detection voice detection |
| gptkbp:standardizedBy |
gptkb:ITU-T
gptkb:AMR_codec gptkb:ETSI gptkb:G.723.1 gptkb:G.729B |
| gptkbp:usedFor |
mobile communications
speech coding noise reduction voice over IP automatic speech recognition speech enhancement detecting presence of human speech |
| gptkbp:usedIn |
speech recognition
telecommunications audio processing |
| gptkbp:bfsParent |
gptkb:G.729B
|
| gptkbp:bfsLayer |
6
|