Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization
Jiangyu Han, Federico Landini, Johan Rohdin, Anna Silnova, Mireia Díez, Jaň Černocký, Lukáš Burget
Topics & Concepts
Computer scienceSpeech recognitionArtificial intelligenceSpeaker diarisationNoise (video)Feature (linguistics)Speaker recognitionSpeaker identificationFace (sociological concept)Key (lock)Speech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing