Yuling Ren
Research Subjects
Research Interests
Yuling Ren has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Han Zhu
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China
1 shared publication - Jiangjiang Zhao
China Mobile Online Services Company Limited China
1 shared publication - Li Wang
Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
1 shared publication - Pengyuan Zhang
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- Open Access
Domain Adaptation Using Class Similarity for Robust Speech Recognition
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from domain mismatch and data sparsity, domain adaptation is very challenging. This paper proposes a novel adaptation method for DNN acoustic model using class similarity. Since the output distribution of DNN model contains the knowledge of similarity among classes, which is applicable to both source and target domain, it could be transferred from source to target model for the performance improvement. In our approach, we first compute the frame level posterior probabilities of source samples using source model. Then, for each class, probabilities of this class are used to compute a mean vector, which we refer to as mean soft labels. During adaptation, these mean soft labels are used in a regularization term to train the target model. Experiments showed that our approach outperforms fine-tuning using one-hot labels on both accent and noise adaptation task, especially when source and target domain are highly mismatched.
Open AccessDomain Adaptation Using Class Similarity for Robust Speech Recognition
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from domain mismatch and data sparsity, domain adaptation is very challenging. This paper proposes a novel adaptation method for DNN acoustic model using class similarity. Since the output distribution of DNN model contains the knowledge of similarity among classes, which is applicable to both source and target domain, it could be transferred from source to target model for the performance improvement. In our approach, we first compute the frame level posterior probabilities of source samples using source model. Then, for each class, probabilities of this class are used to compute a mean vector, which we refer to as mean soft labels. During adaptation, these mean soft labels are used in a regularization term to train the target model. Experiments showed that our approach outperforms fine-tuning using one-hot labels on both accent and noise adaptation task, especially when source and target domain are highly mismatched.