CASA-based speaker identification using cascaded GMM-CNN classifier in noisy and emotional talking conditions
Ali Bou Nassif, Ismail Shahin, Shibani Hamsa, Nawel Nemmour, Keikichi Hirose
Topics & Concepts
Computer scienceSpeech recognitionSpeaker identificationConvolutional neural networkClassifier (UML)Mixture modelArtificial intelligenceIdentification (biology)Pattern recognition (psychology)Speaker diarisationNoise (video)Speaker recognitionImage (mathematics)BiologyBotanySpeech and Audio ProcessingSpeech Recognition and SynthesisMusic and Audio Processing