SpeakerMatchQ

Nicht verfügbar

Formen

SpeakerMatchQ[audio, ref]

SpeakerMatchQ[{audio1, audio2, …}, ref]

SpeakerMatchQ[ref]

Optionen

AcceptanceThreshold — default 0.5
Masking — default All
RecognitionPrior — default 0.5
TargetDevice — default "CPU"

Referenz durchsuchen

Verwandt

FeatureExtractor AudioDistance Classify SpeechRecognize SpeechCases SpeechInterpreter AudioInstanceQ

Alle 6300 Funktionen · Dies aus einem MCP-Client verwenden