[HTML][HTML] A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations
Deep learning has emerged as a powerful tool in various domains, revolutionising machine
learning research. However, one persistent challenge is the scarcity of labelled training …
learning research. However, one persistent challenge is the scarcity of labelled training …
Large-scale self-supervised speech representation learning for automatic speaker verification
The speech representations learned from large-scale unlabeled data have shown better
generalizability than those from supervised learning and thus attract a lot of interest to be …
generalizability than those from supervised learning and thus attract a lot of interest to be …
Pushing the limits of raw waveform speaker recognition
In recent years, speaker recognition systems based on raw waveform inputs have received
increasing attention. However, the performance of such systems are typically inferior to the …
increasing attention. However, the performance of such systems are typically inferior to the …
Self-supervised speaker recognition with loss-gated learning
In self-supervised learning for speaker recognition, pseudo labels are useful as the
supervision signals. It is a known fact that a speaker recognition model doesn't always …
supervision signals. It is a known fact that a speaker recognition model doesn't always …
Self-supervised learning with cluster-aware-dino for high-performance robust speaker verification
The automatic speaker verification task has achieved great success using deep learning
approaches with a large-scale, manually annotated dataset. However, collecting a …
approaches with a large-scale, manually annotated dataset. However, collecting a …
Utilizing self-supervised representations for MOS prediction
Speech quality assessment has been a critical issue in speech processing for decades.
Existing automatic evaluations usually require clean references or parallel ground truth data …
Existing automatic evaluations usually require clean references or parallel ground truth data …
Self-supervised speaker verification using dynamic loss-gate and label correction
For self-supervised speaker verification, the quality of pseudo labels decides the upper
bound of the system due to the massive unreliable labels. In this work, we propose dynamic …
bound of the system due to the massive unreliable labels. In this work, we propose dynamic …
Self-supervised speaker verification with simple siamese network and self-supervised regularization
Training speaker-discriminative and robust speaker verification systems without speaker
labels is still challenging and worthwhile to explore. In this study, we propose an effective …
labels is still challenging and worthwhile to explore. In this study, we propose an effective …
Injecting text in self-supervised speech pretraining
Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied
degrees of success. In this paper, we propose to jointly learn representations during …
degrees of success. In this paper, we propose to jointly learn representations during …
C3-DINO: Joint contrastive and non-contrastive self-supervised learning for speaker verification
Self-supervised learning (SSL) has drawn an increased attention in the field of speech
processing. Recent studies have demonstrated that contrastive learning is able to learn …
processing. Recent studies have demonstrated that contrastive learning is able to learn …