© 2016 IEEE. Multilingual Deep Neural Networks (DNNs) have been successfully used to exploit out-of-language data to improve under-resourced ASR. In this paper, we improve on a multilingual DNN by utilizing low-rank factorization (LRF) of weight matrices via Singular Value Decomposition (SVD) to sparsify a multilingual DNN. LRF was previously used for monolingual DNNs, yielding large computational savings without a significant loss in recognition accuracy. In this work, we show that properly applying LRF on a multilingual DNN can improve recognition accuracy for multiple low-resource ASR configurations. First, only the final weight layer is factorized. Since the output weight layer needs to be trained with language specific data, reducing t...
While Deep Neural Networks (DNNs) have achieved tremen-dous success for large vocabulary continuous ...
In this paper we present our latest investigation on multilingual bottle-neck (BN) features and its ...
We investigate two strategies to improve the context-dependent deep neural network hidden Markov mod...
© 2017 IEEE. DNNs have shown remarkable performance in multilingual scenarios; however, these models...
© 2016 The Authors. Multilingual Deep Neural Networks (DNNs) have been successfully used to leverage...
AbstractMultilingual Deep Neural Networks (DNNs) have been successfully used to leverage out-of-lang...
© 2014 IEEE. Deep neural networks (DNNs) have shown a great promise in exploiting out-of-language da...
When deployed in automated speech recognition (ASR), deep neural networks (DNNs) can be treated as a...
© 2015 IEEE. Recently, multilingual deep neural networks (DNNs) have been successfully used to impro...
This paper presents a study on multilingual deep neural net-work (DNN) based acoustic modeling and i...
We propose a new technique for training deep neural networks (DNNs) as data-driven feature front-end...
The introduction of deep neural networks (DNNs) has advanced the performance of automatic speech rec...
Over the past decades, speech recognition has dramatically improved in a large variety of applicatio...
In this work, we propose several deep neural network architectures that are able to leverage data fr...
International audienceThis paper presents our recent study on low-resource automatic speech recognit...
While Deep Neural Networks (DNNs) have achieved tremen-dous success for large vocabulary continuous ...
In this paper we present our latest investigation on multilingual bottle-neck (BN) features and its ...
We investigate two strategies to improve the context-dependent deep neural network hidden Markov mod...
© 2017 IEEE. DNNs have shown remarkable performance in multilingual scenarios; however, these models...
© 2016 The Authors. Multilingual Deep Neural Networks (DNNs) have been successfully used to leverage...
AbstractMultilingual Deep Neural Networks (DNNs) have been successfully used to leverage out-of-lang...
© 2014 IEEE. Deep neural networks (DNNs) have shown a great promise in exploiting out-of-language da...
When deployed in automated speech recognition (ASR), deep neural networks (DNNs) can be treated as a...
© 2015 IEEE. Recently, multilingual deep neural networks (DNNs) have been successfully used to impro...
This paper presents a study on multilingual deep neural net-work (DNN) based acoustic modeling and i...
We propose a new technique for training deep neural networks (DNNs) as data-driven feature front-end...
The introduction of deep neural networks (DNNs) has advanced the performance of automatic speech rec...
Over the past decades, speech recognition has dramatically improved in a large variety of applicatio...
In this work, we propose several deep neural network architectures that are able to leverage data fr...
International audienceThis paper presents our recent study on low-resource automatic speech recognit...
While Deep Neural Networks (DNNs) have achieved tremen-dous success for large vocabulary continuous ...
In this paper we present our latest investigation on multilingual bottle-neck (BN) features and its ...
We investigate two strategies to improve the context-dependent deep neural network hidden Markov mod...