7 citations · 8 across the 5 of their papers we have counts for
6 papers
DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores
Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee
Mean opinion score (MOS) is a typical subjective evaluation metric for speech synthesis systems. Since collecting MOS is time-consuming, it would be desirable if there are accurate…
On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting
Wei-Tsung Kao, Yuan-Kuei Wu, Chia-Ping Chen +3
User-defined keyword spotting is a task to detect new spoken terms defined by users. This can be viewed as a few-shot learning problem since it is unreasonable for users to define…
Membership Inference Attacks Against Self-supervised Speech Models
Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee
Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can gen…
Utilizing Self-supervised Representations for MOS Prediction
Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao +2
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,…
Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability
Wei-Tsung Kao, Hung-Yi Lee
This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify…
BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT
Wei-Tsung Kao, Tsung-Han Wu, Po-Han Chi +2
Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A…