Modulation Filter Learning Using Deep Variational Networks for Robust Speech Recognition

Agrawal, Purvi; Ganapathy, Sriram

doi:10.1109/jstsp.2019.2913965

Cited by 33 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the last decade, deep learning has demonstrated to be an excellent technique in the field of AI. Deep learning methods have been used to solve various problems like image processing [27,28], speech recognition [29,30], and natural language processing [31,32]. As deep learning can learn robust and effective feature representation through layer-by-layer feature transformation of the original signal automatically, it has a good capability to cope with some challenges in the field of self-driving cars.…”

Section: Theoretical Background Of Deep Learning Methods Used For Selmentioning

confidence: 99%

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

Chen

et al. 2020

Applied Sciences

118

View full text Add to dashboard Cite

Self-driving cars are a hot research topic in science and technology, which has a great influence on social and economic development. Deep learning is one of the current key areas in the field of artificial intelligence research. It has been widely applied in image processing, natural language understanding, and so on. In recent years, more and more deep learning-based solutions have been presented in the field of self-driving cars and have achieved outstanding results. This paper presents a review of recent research on theories and applications of deep learning for self-driving cars. This survey provides a detailed explanation of the developments of self-driving cars and summarizes the applications of deep learning methods in the field of self-driving cars. Then the main problems in self-driving cars and their solutions based on deep learning methods are analyzed, such as obstacle detection, scene recognition, lane detection, navigation and path planning. In addition, the details of some representative approaches for self-driving cars using deep learning methods are summarized. Finally, the future challenges in the applications of deep learning for self-driving cars are given out.

show abstract

Section: Theoretical Background Of Deep Learning Methods Used For Selmentioning

confidence: 99%

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

Chen

et al. 2020

Applied Sciences

118

View full text Add to dashboard Cite

show abstract

“…When the output encounters the token <eos>, it indicates the end of decoding. The decoding process is performed with the beam search strategy [34]. In other words, following each output step, the Speller only keeps the top N paths with the highest probability among all decoding paths.…”

Section: B Decoding Strategymentioning

confidence: 99%

End-to-End Amdo-Tibetan Speech Recognition Based on Knowledge Transfer

Zhu

Huang

2020

IEEE Access

View full text Add to dashboard Cite

The end-to-end speech recognition technology solves the problem that each component is independent and models cannot be jointly optimized in the traditional speech recognition model. It incorporates such components as the acoustic model, language model, and decoding unit of the hybrid model into a single neural network, that can avoid the inherent defects of multiple modules and greatly reduces the complexity of the speech recognition model. In this research, an Amdo-Tibetan speech recognition system is constructed based on Listen, Attend and Spell (LAS) model by the end-to-end speech recognition technology. It can realize the direct conversion from Amdo-Tibetan speech sequence to the corresponding character sequence and greatly reduces the difficulty of building the Amdo-Tibetan speech recognition model. To further improve the performance of the proposed system, the following improvements have been made: firstly, the Multi-Head attention mechanism is introduced to improve the alignment accuracy between state vectors of decoder and encoder; secondly, the label smoothing technique is adopted to solve the problem of over-fitting; thirdly, an N-gram language model is combined with the LAS model to increase the accuracy of speech recognition and the maximum mutual information (MMI) criterion is employed for discriminative training; and finally, transfer learning is utilized to overcome the problem of insufficient training data. Experimental results show that the proposed model can significantly enhance the performance of Amdo-Tibetan speech recognition.

show abstract

“…C ONVOLUTIONAL neural networks (CNNs) [1] are among the most effective machine learning approaches for processing structured, high-dimensional data such as voice recordings, images, and videos and have become indispensable in, e.g., speech recognition [2], [3], audio processing [4], and image classification [5].…”

Section: Introductionmentioning

confidence: 99%

LeanConvNets: Low-Cost Yet Effective Convolutional Neural Networks

Ephrath

Eliasof

Ruthotto

et al. 2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve highdimensional data. A CNN filters the input feature using a network containing spatial convolution operators with compactly supported stencils. In practice, the input data and the hidden features consist of a large number of channels, which in most CNNs are fully coupled by the convolution operators. This coupling leads to immense computational cost in the training and prediction phase. In this paper, we introduce LeanConvNets that are derived by sparsifying fully-coupled operators in existing CNNs. Our goal is to improve the efficiency of CNNs by reducing the number of weights, floating point operations and latency times, with minimal loss of accuracy. Our lean convolution operators involve tuning parameters that controls the trade-off between the network's accuracy and computational costs. These convolutions can be used in a wide range of existing networks, and we exemplify their use in residual networks (ResNets) and U-Nets. Using a range of benchmark problems from image classification and semantic segmentation, we demonstrate that the resulting LeanConvNet's accuracy is close to state-of-the-art networks while being computationally less expensive. In our tests, the lean versions of ResNet and U-net slightly outperforms comparable reduced architectures such as MobileNets and ShuffleNets.

show abstract

Modulation Filter Learning Using Deep Variational Networks for Robust Speech Recognition

Cited by 33 publications

References 37 publications

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

End-to-End Amdo-Tibetan Speech Recognition Based on Knowledge Transfer

LeanConvNets: Low-Cost Yet Effective Convolutional Neural Networks

Contact Info

Product

Resources

About