Log In Sign Up

Domain Adaptation Using Class Similarity for Robust Speech Recognition

by   Han Zhu, et al.

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.


page 1

page 2

page 3

page 4


L-Vector: Neural Label Embedding for Domain Adaptation

We propose a novel neural label embedding (NLE) scheme for the domain ad...

On-target Adaptation

Domain adaptation seeks to mitigate the shift between training on the so...

Probabilistic Filtered Soft Labels for Domain Adaptation

Many domain adaptation (DA) methods aim to project the source and target...

Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition

Unseen data can degrade performance of deep neural net acoustic models. ...

Domain Adaption for Knowledge Tracing

With the rapid development of online education system, knowledge tracing...

Aspect-augmented Adversarial Networks for Domain Adaptation

We introduce a neural method for transfer learning between two (source a...

Acoustic feature learning cross-domain articulatory measurements

Previous work has shown that it is possible to improve speech recognitio...