One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification.
Jungwoo HeoChan-yeong LimJu-ho KimHyun-seo ShinHa-Jin YuPublished in: INTERSPEECH (2023)
Keyphrases
- learning models
- fine tuning
- speaker verification
- pre trained
- classification models
- learning tasks
- semi supervised learning
- machine learning
- conditional random fields
- loss function
- human computer interaction
- image classification
- multimedia
- image processing
- principal component analysis
- supervised learning
- learning problems
- support vector machine
- artificial neural networks
- high dimensional