Domain Adaptation Using Class Similarity For Robust Speech Recognition

Abstract

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 tha

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keyzhu2020domain

Related papers

• Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition (2017)9.92
• Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
• Self-adaptive Soft Voice Activity Detection Using Deep Neural Networks For Robust Speaker Verification (2019)6.77
• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
• Large-scale Domain Adaptation Via Teacher-student Learning (2017)13.93
• Bayesian Learning For Deep Neural Network Adaptation (2020)9.76
• Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition (2018)0.00
• Domain Adaptation For Formant Estimation Using Deep Learning (2016)0.00