Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions
نویسندگان
چکیده
Semi-supervised and cross-lingual knowledge transfer learnings are two strategies for boosting performance of lowresource speech recognition systems. In this paper, we propose a unified knowledge transfer learning method to deal with these two learning tasks. Such a knowledge transfer learning is realized by fine-tuning of Deep Neural Network (DNN). We demonstrate its effectiveness in both monolingual based semisupervised learning task and cross-lingual knowledge transfer learning task. We then combine these two learning strategies to obtain further performance improvement.
منابع مشابه
Exploiting Eigenposteriors for Semi-Supervised Training of DNN Acoustic Models with Sequence Discrimination
Deep neural network (DNN) acoustic models yield posterior probabilities of senone classes. Recent studies support the existence of low-dimensional subspaces underlying senone posteriors. Principal component analysis (PCA) is applied to identify eigenposteriors and perform low-dimensional projection of the training data posteriors. The resulted enhanced posteriors are applied as soft targets for...
متن کاملImproving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization
The success of deep neural network (DNN) acoustic models is partly owed to large amounts of training data available for different applications. This work investigates ways to improve DNN acoustic models for Bluetooth narrowband mobile applications when relatively small amounts of in-domain training data are available. To address the challenge of limited indomain data, we use cross-bandwidth and...
متن کاملImproving semi-supervised deep neural network for keyword search in low resource languages
In this work, we investigate how to improve semi-supervised DNN for low resource languages where the initial systems may have high error rate. We propose using semi-supervised MLP features for DNN training, and we also explore using confidence to improve semi-supervised cross entropy and sequence training. The work conducted in this paper was evaluated under the IARPA Babel program for the keyw...
متن کاملTransfer Learning and Distillation Techniques to Improve the Acoustic Modeling of Low Resource Languages
Deep neural networks (DNN) require large amount of training data to build robust acoustic models for speech recognition tasks. Our work is intended in improving the low-resource language acoustic model to reach a performance comparable to that of a high-resource scenario with the help of data/model parameters from other high-resource languages. we explore transfer learning and distillation meth...
متن کاملCross-lingual transfer learning during supervised training in low resource scenarios
In this study, transfer learning techniques are presented for cross-lingual speech recognition to mitigate the effects of limited availability of data in a target language using data from richly resourced source languages. First, a maximum likelihood (ML) based regularization criterion is used to learn context-dependent Gaussian mixture model (GMM) based hidden Markov model (HMM) parameters for...
متن کامل